Spaces:
Sleeping
Sleeping
till-onethousand
commited on
Commit
·
f723566
1
Parent(s):
5b30004
This view is limited to 50 files because it contains too many changes.
See raw diff
- model/.gitignore +0 -3
- model/cfg/alexnet.cfg +96 -0
- model/cfg/cifar.cfg +121 -0
- model/cfg/cifar.test.cfg +117 -0
- model/cfg/coco.data +8 -0
- model/cfg/combine9k.data +10 -0
- model/cfg/darknet.cfg +120 -0
- model/cfg/darknet19.cfg +205 -0
- model/cfg/darknet19_448.cfg +197 -0
- model/cfg/darknet53.cfg +566 -0
- model/cfg/darknet53_448.cfg +559 -0
- model/cfg/darknet9000.cfg +205 -0
- model/cfg/densenet201.cfg +1951 -0
- model/cfg/extraction.cfg +209 -0
- model/cfg/extraction.conv.cfg +179 -0
- model/cfg/extraction22k.cfg +206 -0
- model/cfg/go.cfg +132 -0
- model/cfg/go.test.cfg +132 -0
- model/cfg/gru.cfg +29 -0
- model/cfg/imagenet1k.data +8 -0
- model/cfg/imagenet22k.dataset +9 -0
- model/cfg/imagenet9k.hierarchy.dataset +9 -0
- model/cfg/jnet-conv.cfg +118 -0
- model/cfg/openimages.data +8 -0
- model/cfg/resnet101.cfg +990 -0
- model/cfg/resnet152.cfg +1460 -0
- model/cfg/resnet18.cfg +228 -0
- model/cfg/resnet34.cfg +392 -0
- model/cfg/resnet50.cfg +510 -0
- model/cfg/resnext101-32x4d.cfg +1053 -0
- model/cfg/resnext152-32x4d.cfg +1562 -0
- model/cfg/resnext50.cfg +523 -0
- model/cfg/rnn.cfg +38 -0
- model/cfg/rnn.train.cfg +38 -0
- model/cfg/strided.cfg +182 -0
- model/cfg/t1.test.cfg +117 -0
- model/cfg/tiny.cfg +174 -0
- model/cfg/vgg-16.cfg +157 -0
- model/cfg/vgg-conv.cfg +121 -0
- model/cfg/voc.data +6 -0
- model/cfg/writing.cfg +41 -0
- model/cfg/yolo9000.cfg +218 -0
- model/cfg/yolov1-tiny.cfg +130 -0
- model/cfg/yolov1.cfg +261 -0
- model/cfg/yolov2-tiny-voc.cfg +138 -0
- model/cfg/yolov2-tiny.cfg +139 -0
- model/cfg/yolov2-voc.cfg +258 -0
- model/cfg/yolov2.cfg +258 -0
- model/cfg/yolov3-openimages.cfg +789 -0
- model/cfg/yolov3-spp.cfg +822 -0
model/.gitignore
CHANGED
@@ -7,7 +7,6 @@
|
|
7 |
*.pyc
|
8 |
old/
|
9 |
mnist/
|
10 |
-
data/
|
11 |
caffe/
|
12 |
grasp/
|
13 |
images/
|
@@ -15,8 +14,6 @@ opencv/
|
|
15 |
convnet/
|
16 |
decaf/
|
17 |
submission/
|
18 |
-
cfg/
|
19 |
-
darknet
|
20 |
.fuse*
|
21 |
|
22 |
# OS Generated #
|
|
|
7 |
*.pyc
|
8 |
old/
|
9 |
mnist/
|
|
|
10 |
caffe/
|
11 |
grasp/
|
12 |
images/
|
|
|
14 |
convnet/
|
15 |
decaf/
|
16 |
submission/
|
|
|
|
|
17 |
.fuse*
|
18 |
|
19 |
# OS Generated #
|
model/cfg/alexnet.cfg
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=1
|
5 |
+
# Testing
|
6 |
+
batch=1
|
7 |
+
subdivisions=1
|
8 |
+
height=227
|
9 |
+
width=227
|
10 |
+
channels=3
|
11 |
+
momentum=0.9
|
12 |
+
decay=0.0005
|
13 |
+
max_crop=256
|
14 |
+
|
15 |
+
learning_rate=0.01
|
16 |
+
policy=poly
|
17 |
+
power=4
|
18 |
+
max_batches=800000
|
19 |
+
|
20 |
+
angle=7
|
21 |
+
hue = .1
|
22 |
+
saturation=.75
|
23 |
+
exposure=.75
|
24 |
+
aspect=.75
|
25 |
+
|
26 |
+
[convolutional]
|
27 |
+
filters=96
|
28 |
+
size=11
|
29 |
+
stride=4
|
30 |
+
pad=0
|
31 |
+
activation=relu
|
32 |
+
|
33 |
+
[maxpool]
|
34 |
+
size=3
|
35 |
+
stride=2
|
36 |
+
padding=0
|
37 |
+
|
38 |
+
[convolutional]
|
39 |
+
filters=256
|
40 |
+
size=5
|
41 |
+
stride=1
|
42 |
+
pad=1
|
43 |
+
activation=relu
|
44 |
+
|
45 |
+
[maxpool]
|
46 |
+
size=3
|
47 |
+
stride=2
|
48 |
+
padding=0
|
49 |
+
|
50 |
+
[convolutional]
|
51 |
+
filters=384
|
52 |
+
size=3
|
53 |
+
stride=1
|
54 |
+
pad=1
|
55 |
+
activation=relu
|
56 |
+
|
57 |
+
[convolutional]
|
58 |
+
filters=384
|
59 |
+
size=3
|
60 |
+
stride=1
|
61 |
+
pad=1
|
62 |
+
activation=relu
|
63 |
+
|
64 |
+
[convolutional]
|
65 |
+
filters=256
|
66 |
+
size=3
|
67 |
+
stride=1
|
68 |
+
pad=1
|
69 |
+
activation=relu
|
70 |
+
|
71 |
+
[maxpool]
|
72 |
+
size=3
|
73 |
+
stride=2
|
74 |
+
padding=0
|
75 |
+
|
76 |
+
[connected]
|
77 |
+
output=4096
|
78 |
+
activation=relu
|
79 |
+
|
80 |
+
[dropout]
|
81 |
+
probability=.5
|
82 |
+
|
83 |
+
[connected]
|
84 |
+
output=4096
|
85 |
+
activation=relu
|
86 |
+
|
87 |
+
[dropout]
|
88 |
+
probability=.5
|
89 |
+
|
90 |
+
[connected]
|
91 |
+
output=1000
|
92 |
+
activation=linear
|
93 |
+
|
94 |
+
[softmax]
|
95 |
+
groups=1
|
96 |
+
|
model/cfg/cifar.cfg
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=128
|
3 |
+
subdivisions=1
|
4 |
+
height=28
|
5 |
+
width=28
|
6 |
+
channels=3
|
7 |
+
max_crop=32
|
8 |
+
min_crop=32
|
9 |
+
|
10 |
+
hue=.1
|
11 |
+
saturation=.75
|
12 |
+
exposure=.75
|
13 |
+
|
14 |
+
learning_rate=0.4
|
15 |
+
policy=poly
|
16 |
+
power=4
|
17 |
+
max_batches = 5000
|
18 |
+
momentum=0.9
|
19 |
+
decay=0.0005
|
20 |
+
|
21 |
+
|
22 |
+
[convolutional]
|
23 |
+
batch_normalize=1
|
24 |
+
filters=128
|
25 |
+
size=3
|
26 |
+
stride=1
|
27 |
+
pad=1
|
28 |
+
activation=leaky
|
29 |
+
|
30 |
+
[convolutional]
|
31 |
+
batch_normalize=1
|
32 |
+
filters=128
|
33 |
+
size=3
|
34 |
+
stride=1
|
35 |
+
pad=1
|
36 |
+
activation=leaky
|
37 |
+
|
38 |
+
[convolutional]
|
39 |
+
batch_normalize=1
|
40 |
+
filters=128
|
41 |
+
size=3
|
42 |
+
stride=1
|
43 |
+
pad=1
|
44 |
+
activation=leaky
|
45 |
+
|
46 |
+
[maxpool]
|
47 |
+
size=2
|
48 |
+
stride=2
|
49 |
+
|
50 |
+
[dropout]
|
51 |
+
probability=.5
|
52 |
+
|
53 |
+
[convolutional]
|
54 |
+
batch_normalize=1
|
55 |
+
filters=256
|
56 |
+
size=3
|
57 |
+
stride=1
|
58 |
+
pad=1
|
59 |
+
activation=leaky
|
60 |
+
|
61 |
+
[convolutional]
|
62 |
+
batch_normalize=1
|
63 |
+
filters=256
|
64 |
+
size=3
|
65 |
+
stride=1
|
66 |
+
pad=1
|
67 |
+
activation=leaky
|
68 |
+
|
69 |
+
[convolutional]
|
70 |
+
batch_normalize=1
|
71 |
+
filters=256
|
72 |
+
size=3
|
73 |
+
stride=1
|
74 |
+
pad=1
|
75 |
+
activation=leaky
|
76 |
+
|
77 |
+
[maxpool]
|
78 |
+
size=2
|
79 |
+
stride=2
|
80 |
+
|
81 |
+
[dropout]
|
82 |
+
probability=.5
|
83 |
+
|
84 |
+
[convolutional]
|
85 |
+
batch_normalize=1
|
86 |
+
filters=512
|
87 |
+
size=3
|
88 |
+
stride=1
|
89 |
+
pad=1
|
90 |
+
activation=leaky
|
91 |
+
|
92 |
+
[convolutional]
|
93 |
+
batch_normalize=1
|
94 |
+
filters=512
|
95 |
+
size=3
|
96 |
+
stride=1
|
97 |
+
pad=1
|
98 |
+
activation=leaky
|
99 |
+
|
100 |
+
[convolutional]
|
101 |
+
batch_normalize=1
|
102 |
+
filters=512
|
103 |
+
size=3
|
104 |
+
stride=1
|
105 |
+
pad=1
|
106 |
+
activation=leaky
|
107 |
+
|
108 |
+
[dropout]
|
109 |
+
probability=.5
|
110 |
+
|
111 |
+
[convolutional]
|
112 |
+
filters=10
|
113 |
+
size=1
|
114 |
+
stride=1
|
115 |
+
pad=1
|
116 |
+
activation=leaky
|
117 |
+
|
118 |
+
[avgpool]
|
119 |
+
|
120 |
+
[softmax]
|
121 |
+
groups=1
|
model/cfg/cifar.test.cfg
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=128
|
3 |
+
subdivisions=1
|
4 |
+
height=32
|
5 |
+
width=32
|
6 |
+
channels=3
|
7 |
+
momentum=0.9
|
8 |
+
decay=0.0005
|
9 |
+
|
10 |
+
learning_rate=0.4
|
11 |
+
policy=poly
|
12 |
+
power=4
|
13 |
+
max_batches = 50000
|
14 |
+
|
15 |
+
|
16 |
+
[convolutional]
|
17 |
+
batch_normalize=1
|
18 |
+
filters=128
|
19 |
+
size=3
|
20 |
+
stride=1
|
21 |
+
pad=1
|
22 |
+
activation=leaky
|
23 |
+
|
24 |
+
[convolutional]
|
25 |
+
batch_normalize=1
|
26 |
+
filters=128
|
27 |
+
size=3
|
28 |
+
stride=1
|
29 |
+
pad=1
|
30 |
+
activation=leaky
|
31 |
+
|
32 |
+
[convolutional]
|
33 |
+
batch_normalize=1
|
34 |
+
filters=128
|
35 |
+
size=3
|
36 |
+
stride=1
|
37 |
+
pad=1
|
38 |
+
activation=leaky
|
39 |
+
|
40 |
+
[maxpool]
|
41 |
+
size=2
|
42 |
+
stride=2
|
43 |
+
|
44 |
+
[dropout]
|
45 |
+
probability=.5
|
46 |
+
|
47 |
+
[convolutional]
|
48 |
+
batch_normalize=1
|
49 |
+
filters=256
|
50 |
+
size=3
|
51 |
+
stride=1
|
52 |
+
pad=1
|
53 |
+
activation=leaky
|
54 |
+
|
55 |
+
[convolutional]
|
56 |
+
batch_normalize=1
|
57 |
+
filters=256
|
58 |
+
size=3
|
59 |
+
stride=1
|
60 |
+
pad=1
|
61 |
+
activation=leaky
|
62 |
+
|
63 |
+
[convolutional]
|
64 |
+
batch_normalize=1
|
65 |
+
filters=256
|
66 |
+
size=3
|
67 |
+
stride=1
|
68 |
+
pad=1
|
69 |
+
activation=leaky
|
70 |
+
|
71 |
+
[maxpool]
|
72 |
+
size=2
|
73 |
+
stride=2
|
74 |
+
|
75 |
+
[dropout]
|
76 |
+
probability=.5
|
77 |
+
|
78 |
+
[convolutional]
|
79 |
+
batch_normalize=1
|
80 |
+
filters=512
|
81 |
+
size=3
|
82 |
+
stride=1
|
83 |
+
pad=1
|
84 |
+
activation=leaky
|
85 |
+
|
86 |
+
[convolutional]
|
87 |
+
batch_normalize=1
|
88 |
+
filters=512
|
89 |
+
size=3
|
90 |
+
stride=1
|
91 |
+
pad=1
|
92 |
+
activation=leaky
|
93 |
+
|
94 |
+
[convolutional]
|
95 |
+
batch_normalize=1
|
96 |
+
filters=512
|
97 |
+
size=3
|
98 |
+
stride=1
|
99 |
+
pad=1
|
100 |
+
activation=leaky
|
101 |
+
|
102 |
+
[dropout]
|
103 |
+
probability=.5
|
104 |
+
|
105 |
+
[convolutional]
|
106 |
+
filters=10
|
107 |
+
size=1
|
108 |
+
stride=1
|
109 |
+
pad=1
|
110 |
+
activation=leaky
|
111 |
+
|
112 |
+
[avgpool]
|
113 |
+
|
114 |
+
[softmax]
|
115 |
+
groups=1
|
116 |
+
temperature=3
|
117 |
+
|
model/cfg/coco.data
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
classes= 80
|
2 |
+
train = /home/pjreddie/data/coco/trainvalno5k.txt
|
3 |
+
valid = coco_testdev
|
4 |
+
#valid = data/coco_val_5k.list
|
5 |
+
names = data/coco.names
|
6 |
+
backup = /home/pjreddie/backup/
|
7 |
+
eval=coco
|
8 |
+
|
model/cfg/combine9k.data
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
classes= 9418
|
2 |
+
#train = /home/pjreddie/data/coco/trainvalno5k.txt
|
3 |
+
train = data/combine9k.train.list
|
4 |
+
valid = /home/pjreddie/data/imagenet/det.val.files
|
5 |
+
labels = data/9k.labels
|
6 |
+
names = data/9k.names
|
7 |
+
backup = backup/
|
8 |
+
map = data/inet9k.map
|
9 |
+
eval = imagenet
|
10 |
+
results = results
|
model/cfg/darknet.cfg
ADDED
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=1
|
5 |
+
# Testing
|
6 |
+
batch=1
|
7 |
+
subdivisions=1
|
8 |
+
height=256
|
9 |
+
width=256
|
10 |
+
min_crop=128
|
11 |
+
max_crop=448
|
12 |
+
channels=3
|
13 |
+
momentum=0.9
|
14 |
+
decay=0.0005
|
15 |
+
|
16 |
+
burn_in=1000
|
17 |
+
learning_rate=0.1
|
18 |
+
policy=poly
|
19 |
+
power=4
|
20 |
+
max_batches=800000
|
21 |
+
|
22 |
+
angle=7
|
23 |
+
hue=.1
|
24 |
+
saturation=.75
|
25 |
+
exposure=.75
|
26 |
+
aspect=.75
|
27 |
+
|
28 |
+
|
29 |
+
[convolutional]
|
30 |
+
batch_normalize=1
|
31 |
+
filters=16
|
32 |
+
size=3
|
33 |
+
stride=1
|
34 |
+
pad=1
|
35 |
+
activation=leaky
|
36 |
+
|
37 |
+
[maxpool]
|
38 |
+
size=2
|
39 |
+
stride=2
|
40 |
+
|
41 |
+
[convolutional]
|
42 |
+
batch_normalize=1
|
43 |
+
filters=32
|
44 |
+
size=3
|
45 |
+
stride=1
|
46 |
+
pad=1
|
47 |
+
activation=leaky
|
48 |
+
|
49 |
+
[maxpool]
|
50 |
+
size=2
|
51 |
+
stride=2
|
52 |
+
|
53 |
+
[convolutional]
|
54 |
+
batch_normalize=1
|
55 |
+
filters=64
|
56 |
+
size=3
|
57 |
+
stride=1
|
58 |
+
pad=1
|
59 |
+
activation=leaky
|
60 |
+
|
61 |
+
[maxpool]
|
62 |
+
size=2
|
63 |
+
stride=2
|
64 |
+
|
65 |
+
[convolutional]
|
66 |
+
batch_normalize=1
|
67 |
+
filters=128
|
68 |
+
size=3
|
69 |
+
stride=1
|
70 |
+
pad=1
|
71 |
+
activation=leaky
|
72 |
+
|
73 |
+
[maxpool]
|
74 |
+
size=2
|
75 |
+
stride=2
|
76 |
+
|
77 |
+
[convolutional]
|
78 |
+
batch_normalize=1
|
79 |
+
filters=256
|
80 |
+
size=3
|
81 |
+
stride=1
|
82 |
+
pad=1
|
83 |
+
activation=leaky
|
84 |
+
|
85 |
+
[maxpool]
|
86 |
+
size=2
|
87 |
+
stride=2
|
88 |
+
|
89 |
+
[convolutional]
|
90 |
+
batch_normalize=1
|
91 |
+
filters=512
|
92 |
+
size=3
|
93 |
+
stride=1
|
94 |
+
pad=1
|
95 |
+
activation=leaky
|
96 |
+
|
97 |
+
[maxpool]
|
98 |
+
size=2
|
99 |
+
stride=2
|
100 |
+
|
101 |
+
[convolutional]
|
102 |
+
batch_normalize=1
|
103 |
+
filters=1024
|
104 |
+
size=3
|
105 |
+
stride=1
|
106 |
+
pad=1
|
107 |
+
activation=leaky
|
108 |
+
|
109 |
+
[avgpool]
|
110 |
+
|
111 |
+
[convolutional]
|
112 |
+
filters=1000
|
113 |
+
size=1
|
114 |
+
stride=1
|
115 |
+
pad=1
|
116 |
+
activation=linear
|
117 |
+
|
118 |
+
[softmax]
|
119 |
+
groups=1
|
120 |
+
|
model/cfg/darknet19.cfg
ADDED
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
#batch=128
|
4 |
+
#subdivisions=2
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
min_crop=128
|
13 |
+
max_crop=448
|
14 |
+
channels=3
|
15 |
+
momentum=0.9
|
16 |
+
decay=0.0005
|
17 |
+
|
18 |
+
burn_in=1000
|
19 |
+
learning_rate=0.1
|
20 |
+
policy=poly
|
21 |
+
power=4
|
22 |
+
max_batches=800000
|
23 |
+
|
24 |
+
angle=7
|
25 |
+
hue=.1
|
26 |
+
saturation=.75
|
27 |
+
exposure=.75
|
28 |
+
aspect=.75
|
29 |
+
|
30 |
+
[convolutional]
|
31 |
+
batch_normalize=1
|
32 |
+
filters=32
|
33 |
+
size=3
|
34 |
+
stride=1
|
35 |
+
pad=1
|
36 |
+
activation=leaky
|
37 |
+
|
38 |
+
[maxpool]
|
39 |
+
size=2
|
40 |
+
stride=2
|
41 |
+
|
42 |
+
[convolutional]
|
43 |
+
batch_normalize=1
|
44 |
+
filters=64
|
45 |
+
size=3
|
46 |
+
stride=1
|
47 |
+
pad=1
|
48 |
+
activation=leaky
|
49 |
+
|
50 |
+
[maxpool]
|
51 |
+
size=2
|
52 |
+
stride=2
|
53 |
+
|
54 |
+
[convolutional]
|
55 |
+
batch_normalize=1
|
56 |
+
filters=128
|
57 |
+
size=3
|
58 |
+
stride=1
|
59 |
+
pad=1
|
60 |
+
activation=leaky
|
61 |
+
|
62 |
+
[convolutional]
|
63 |
+
batch_normalize=1
|
64 |
+
filters=64
|
65 |
+
size=1
|
66 |
+
stride=1
|
67 |
+
pad=1
|
68 |
+
activation=leaky
|
69 |
+
|
70 |
+
[convolutional]
|
71 |
+
batch_normalize=1
|
72 |
+
filters=128
|
73 |
+
size=3
|
74 |
+
stride=1
|
75 |
+
pad=1
|
76 |
+
activation=leaky
|
77 |
+
|
78 |
+
[maxpool]
|
79 |
+
size=2
|
80 |
+
stride=2
|
81 |
+
|
82 |
+
[convolutional]
|
83 |
+
batch_normalize=1
|
84 |
+
filters=256
|
85 |
+
size=3
|
86 |
+
stride=1
|
87 |
+
pad=1
|
88 |
+
activation=leaky
|
89 |
+
|
90 |
+
[convolutional]
|
91 |
+
batch_normalize=1
|
92 |
+
filters=128
|
93 |
+
size=1
|
94 |
+
stride=1
|
95 |
+
pad=1
|
96 |
+
activation=leaky
|
97 |
+
|
98 |
+
[convolutional]
|
99 |
+
batch_normalize=1
|
100 |
+
filters=256
|
101 |
+
size=3
|
102 |
+
stride=1
|
103 |
+
pad=1
|
104 |
+
activation=leaky
|
105 |
+
|
106 |
+
[maxpool]
|
107 |
+
size=2
|
108 |
+
stride=2
|
109 |
+
|
110 |
+
[convolutional]
|
111 |
+
batch_normalize=1
|
112 |
+
filters=512
|
113 |
+
size=3
|
114 |
+
stride=1
|
115 |
+
pad=1
|
116 |
+
activation=leaky
|
117 |
+
|
118 |
+
[convolutional]
|
119 |
+
batch_normalize=1
|
120 |
+
filters=256
|
121 |
+
size=1
|
122 |
+
stride=1
|
123 |
+
pad=1
|
124 |
+
activation=leaky
|
125 |
+
|
126 |
+
[convolutional]
|
127 |
+
batch_normalize=1
|
128 |
+
filters=512
|
129 |
+
size=3
|
130 |
+
stride=1
|
131 |
+
pad=1
|
132 |
+
activation=leaky
|
133 |
+
|
134 |
+
[convolutional]
|
135 |
+
batch_normalize=1
|
136 |
+
filters=256
|
137 |
+
size=1
|
138 |
+
stride=1
|
139 |
+
pad=1
|
140 |
+
activation=leaky
|
141 |
+
|
142 |
+
[convolutional]
|
143 |
+
batch_normalize=1
|
144 |
+
filters=512
|
145 |
+
size=3
|
146 |
+
stride=1
|
147 |
+
pad=1
|
148 |
+
activation=leaky
|
149 |
+
|
150 |
+
[maxpool]
|
151 |
+
size=2
|
152 |
+
stride=2
|
153 |
+
|
154 |
+
[convolutional]
|
155 |
+
batch_normalize=1
|
156 |
+
filters=1024
|
157 |
+
size=3
|
158 |
+
stride=1
|
159 |
+
pad=1
|
160 |
+
activation=leaky
|
161 |
+
|
162 |
+
[convolutional]
|
163 |
+
batch_normalize=1
|
164 |
+
filters=512
|
165 |
+
size=1
|
166 |
+
stride=1
|
167 |
+
pad=1
|
168 |
+
activation=leaky
|
169 |
+
|
170 |
+
[convolutional]
|
171 |
+
batch_normalize=1
|
172 |
+
filters=1024
|
173 |
+
size=3
|
174 |
+
stride=1
|
175 |
+
pad=1
|
176 |
+
activation=leaky
|
177 |
+
|
178 |
+
[convolutional]
|
179 |
+
batch_normalize=1
|
180 |
+
filters=512
|
181 |
+
size=1
|
182 |
+
stride=1
|
183 |
+
pad=1
|
184 |
+
activation=leaky
|
185 |
+
|
186 |
+
[convolutional]
|
187 |
+
batch_normalize=1
|
188 |
+
filters=1024
|
189 |
+
size=3
|
190 |
+
stride=1
|
191 |
+
pad=1
|
192 |
+
activation=leaky
|
193 |
+
|
194 |
+
[convolutional]
|
195 |
+
filters=1000
|
196 |
+
size=1
|
197 |
+
stride=1
|
198 |
+
pad=1
|
199 |
+
activation=linear
|
200 |
+
|
201 |
+
[avgpool]
|
202 |
+
|
203 |
+
[softmax]
|
204 |
+
groups=1
|
205 |
+
|
model/cfg/darknet19_448.cfg
ADDED
@@ -0,0 +1,197 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=128
|
3 |
+
subdivisions=4
|
4 |
+
height=448
|
5 |
+
width=448
|
6 |
+
max_crop=512
|
7 |
+
channels=3
|
8 |
+
momentum=0.9
|
9 |
+
decay=0.0005
|
10 |
+
|
11 |
+
learning_rate=0.001
|
12 |
+
policy=poly
|
13 |
+
power=4
|
14 |
+
max_batches=100000
|
15 |
+
|
16 |
+
angle=7
|
17 |
+
hue = .1
|
18 |
+
saturation=.75
|
19 |
+
exposure=.75
|
20 |
+
aspect=.75
|
21 |
+
|
22 |
+
[convolutional]
|
23 |
+
batch_normalize=1
|
24 |
+
filters=32
|
25 |
+
size=3
|
26 |
+
stride=1
|
27 |
+
pad=1
|
28 |
+
activation=leaky
|
29 |
+
|
30 |
+
[maxpool]
|
31 |
+
size=2
|
32 |
+
stride=2
|
33 |
+
|
34 |
+
[convolutional]
|
35 |
+
batch_normalize=1
|
36 |
+
filters=64
|
37 |
+
size=3
|
38 |
+
stride=1
|
39 |
+
pad=1
|
40 |
+
activation=leaky
|
41 |
+
|
42 |
+
[maxpool]
|
43 |
+
size=2
|
44 |
+
stride=2
|
45 |
+
|
46 |
+
[convolutional]
|
47 |
+
batch_normalize=1
|
48 |
+
filters=128
|
49 |
+
size=3
|
50 |
+
stride=1
|
51 |
+
pad=1
|
52 |
+
activation=leaky
|
53 |
+
|
54 |
+
[convolutional]
|
55 |
+
batch_normalize=1
|
56 |
+
filters=64
|
57 |
+
size=1
|
58 |
+
stride=1
|
59 |
+
pad=1
|
60 |
+
activation=leaky
|
61 |
+
|
62 |
+
[convolutional]
|
63 |
+
batch_normalize=1
|
64 |
+
filters=128
|
65 |
+
size=3
|
66 |
+
stride=1
|
67 |
+
pad=1
|
68 |
+
activation=leaky
|
69 |
+
|
70 |
+
[maxpool]
|
71 |
+
size=2
|
72 |
+
stride=2
|
73 |
+
|
74 |
+
[convolutional]
|
75 |
+
batch_normalize=1
|
76 |
+
filters=256
|
77 |
+
size=3
|
78 |
+
stride=1
|
79 |
+
pad=1
|
80 |
+
activation=leaky
|
81 |
+
|
82 |
+
[convolutional]
|
83 |
+
batch_normalize=1
|
84 |
+
filters=128
|
85 |
+
size=1
|
86 |
+
stride=1
|
87 |
+
pad=1
|
88 |
+
activation=leaky
|
89 |
+
|
90 |
+
[convolutional]
|
91 |
+
batch_normalize=1
|
92 |
+
filters=256
|
93 |
+
size=3
|
94 |
+
stride=1
|
95 |
+
pad=1
|
96 |
+
activation=leaky
|
97 |
+
|
98 |
+
[maxpool]
|
99 |
+
size=2
|
100 |
+
stride=2
|
101 |
+
|
102 |
+
[convolutional]
|
103 |
+
batch_normalize=1
|
104 |
+
filters=512
|
105 |
+
size=3
|
106 |
+
stride=1
|
107 |
+
pad=1
|
108 |
+
activation=leaky
|
109 |
+
|
110 |
+
[convolutional]
|
111 |
+
batch_normalize=1
|
112 |
+
filters=256
|
113 |
+
size=1
|
114 |
+
stride=1
|
115 |
+
pad=1
|
116 |
+
activation=leaky
|
117 |
+
|
118 |
+
[convolutional]
|
119 |
+
batch_normalize=1
|
120 |
+
filters=512
|
121 |
+
size=3
|
122 |
+
stride=1
|
123 |
+
pad=1
|
124 |
+
activation=leaky
|
125 |
+
|
126 |
+
[convolutional]
|
127 |
+
batch_normalize=1
|
128 |
+
filters=256
|
129 |
+
size=1
|
130 |
+
stride=1
|
131 |
+
pad=1
|
132 |
+
activation=leaky
|
133 |
+
|
134 |
+
[convolutional]
|
135 |
+
batch_normalize=1
|
136 |
+
filters=512
|
137 |
+
size=3
|
138 |
+
stride=1
|
139 |
+
pad=1
|
140 |
+
activation=leaky
|
141 |
+
|
142 |
+
[maxpool]
|
143 |
+
size=2
|
144 |
+
stride=2
|
145 |
+
|
146 |
+
[convolutional]
|
147 |
+
batch_normalize=1
|
148 |
+
filters=1024
|
149 |
+
size=3
|
150 |
+
stride=1
|
151 |
+
pad=1
|
152 |
+
activation=leaky
|
153 |
+
|
154 |
+
[convolutional]
|
155 |
+
batch_normalize=1
|
156 |
+
filters=512
|
157 |
+
size=1
|
158 |
+
stride=1
|
159 |
+
pad=1
|
160 |
+
activation=leaky
|
161 |
+
|
162 |
+
[convolutional]
|
163 |
+
batch_normalize=1
|
164 |
+
filters=1024
|
165 |
+
size=3
|
166 |
+
stride=1
|
167 |
+
pad=1
|
168 |
+
activation=leaky
|
169 |
+
|
170 |
+
[convolutional]
|
171 |
+
batch_normalize=1
|
172 |
+
filters=512
|
173 |
+
size=1
|
174 |
+
stride=1
|
175 |
+
pad=1
|
176 |
+
activation=leaky
|
177 |
+
|
178 |
+
[convolutional]
|
179 |
+
batch_normalize=1
|
180 |
+
filters=1024
|
181 |
+
size=3
|
182 |
+
stride=1
|
183 |
+
pad=1
|
184 |
+
activation=leaky
|
185 |
+
|
186 |
+
[convolutional]
|
187 |
+
filters=1000
|
188 |
+
size=1
|
189 |
+
stride=1
|
190 |
+
pad=1
|
191 |
+
activation=linear
|
192 |
+
|
193 |
+
[avgpool]
|
194 |
+
|
195 |
+
[softmax]
|
196 |
+
groups=1
|
197 |
+
|
model/cfg/darknet53.cfg
ADDED
@@ -0,0 +1,566 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=4
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
channels=3
|
13 |
+
min_crop=128
|
14 |
+
max_crop=448
|
15 |
+
|
16 |
+
burn_in=1000
|
17 |
+
learning_rate=0.1
|
18 |
+
policy=poly
|
19 |
+
power=4
|
20 |
+
max_batches=800000
|
21 |
+
momentum=0.9
|
22 |
+
decay=0.0005
|
23 |
+
|
24 |
+
angle=7
|
25 |
+
hue=.1
|
26 |
+
saturation=.75
|
27 |
+
exposure=.75
|
28 |
+
aspect=.75
|
29 |
+
|
30 |
+
|
31 |
+
[convolutional]
|
32 |
+
batch_normalize=1
|
33 |
+
filters=32
|
34 |
+
size=3
|
35 |
+
stride=1
|
36 |
+
pad=1
|
37 |
+
activation=leaky
|
38 |
+
|
39 |
+
# Downsample
|
40 |
+
|
41 |
+
[convolutional]
|
42 |
+
batch_normalize=1
|
43 |
+
filters=64
|
44 |
+
size=3
|
45 |
+
stride=2
|
46 |
+
pad=1
|
47 |
+
activation=leaky
|
48 |
+
|
49 |
+
[convolutional]
|
50 |
+
batch_normalize=1
|
51 |
+
filters=32
|
52 |
+
size=1
|
53 |
+
stride=1
|
54 |
+
pad=1
|
55 |
+
activation=leaky
|
56 |
+
|
57 |
+
[convolutional]
|
58 |
+
batch_normalize=1
|
59 |
+
filters=64
|
60 |
+
size=3
|
61 |
+
stride=1
|
62 |
+
pad=1
|
63 |
+
activation=leaky
|
64 |
+
|
65 |
+
[shortcut]
|
66 |
+
from=-3
|
67 |
+
activation=linear
|
68 |
+
|
69 |
+
# Downsample
|
70 |
+
|
71 |
+
[convolutional]
|
72 |
+
batch_normalize=1
|
73 |
+
filters=128
|
74 |
+
size=3
|
75 |
+
stride=2
|
76 |
+
pad=1
|
77 |
+
activation=leaky
|
78 |
+
|
79 |
+
[convolutional]
|
80 |
+
batch_normalize=1
|
81 |
+
filters=64
|
82 |
+
size=1
|
83 |
+
stride=1
|
84 |
+
pad=1
|
85 |
+
activation=leaky
|
86 |
+
|
87 |
+
[convolutional]
|
88 |
+
batch_normalize=1
|
89 |
+
filters=128
|
90 |
+
size=3
|
91 |
+
stride=1
|
92 |
+
pad=1
|
93 |
+
activation=leaky
|
94 |
+
|
95 |
+
[shortcut]
|
96 |
+
from=-3
|
97 |
+
activation=linear
|
98 |
+
|
99 |
+
[convolutional]
|
100 |
+
batch_normalize=1
|
101 |
+
filters=64
|
102 |
+
size=1
|
103 |
+
stride=1
|
104 |
+
pad=1
|
105 |
+
activation=leaky
|
106 |
+
|
107 |
+
[convolutional]
|
108 |
+
batch_normalize=1
|
109 |
+
filters=128
|
110 |
+
size=3
|
111 |
+
stride=1
|
112 |
+
pad=1
|
113 |
+
activation=leaky
|
114 |
+
|
115 |
+
[shortcut]
|
116 |
+
from=-3
|
117 |
+
activation=linear
|
118 |
+
|
119 |
+
# Downsample
|
120 |
+
|
121 |
+
[convolutional]
|
122 |
+
batch_normalize=1
|
123 |
+
filters=256
|
124 |
+
size=3
|
125 |
+
stride=2
|
126 |
+
pad=1
|
127 |
+
activation=leaky
|
128 |
+
|
129 |
+
[convolutional]
|
130 |
+
batch_normalize=1
|
131 |
+
filters=128
|
132 |
+
size=1
|
133 |
+
stride=1
|
134 |
+
pad=1
|
135 |
+
activation=leaky
|
136 |
+
|
137 |
+
[convolutional]
|
138 |
+
batch_normalize=1
|
139 |
+
filters=256
|
140 |
+
size=3
|
141 |
+
stride=1
|
142 |
+
pad=1
|
143 |
+
activation=leaky
|
144 |
+
|
145 |
+
[shortcut]
|
146 |
+
from=-3
|
147 |
+
activation=linear
|
148 |
+
|
149 |
+
[convolutional]
|
150 |
+
batch_normalize=1
|
151 |
+
filters=128
|
152 |
+
size=1
|
153 |
+
stride=1
|
154 |
+
pad=1
|
155 |
+
activation=leaky
|
156 |
+
|
157 |
+
[convolutional]
|
158 |
+
batch_normalize=1
|
159 |
+
filters=256
|
160 |
+
size=3
|
161 |
+
stride=1
|
162 |
+
pad=1
|
163 |
+
activation=leaky
|
164 |
+
|
165 |
+
[shortcut]
|
166 |
+
from=-3
|
167 |
+
activation=linear
|
168 |
+
|
169 |
+
[convolutional]
|
170 |
+
batch_normalize=1
|
171 |
+
filters=128
|
172 |
+
size=1
|
173 |
+
stride=1
|
174 |
+
pad=1
|
175 |
+
activation=leaky
|
176 |
+
|
177 |
+
[convolutional]
|
178 |
+
batch_normalize=1
|
179 |
+
filters=256
|
180 |
+
size=3
|
181 |
+
stride=1
|
182 |
+
pad=1
|
183 |
+
activation=leaky
|
184 |
+
|
185 |
+
[shortcut]
|
186 |
+
from=-3
|
187 |
+
activation=linear
|
188 |
+
|
189 |
+
[convolutional]
|
190 |
+
batch_normalize=1
|
191 |
+
filters=128
|
192 |
+
size=1
|
193 |
+
stride=1
|
194 |
+
pad=1
|
195 |
+
activation=leaky
|
196 |
+
|
197 |
+
[convolutional]
|
198 |
+
batch_normalize=1
|
199 |
+
filters=256
|
200 |
+
size=3
|
201 |
+
stride=1
|
202 |
+
pad=1
|
203 |
+
activation=leaky
|
204 |
+
|
205 |
+
[shortcut]
|
206 |
+
from=-3
|
207 |
+
activation=linear
|
208 |
+
|
209 |
+
|
210 |
+
[convolutional]
|
211 |
+
batch_normalize=1
|
212 |
+
filters=128
|
213 |
+
size=1
|
214 |
+
stride=1
|
215 |
+
pad=1
|
216 |
+
activation=leaky
|
217 |
+
|
218 |
+
[convolutional]
|
219 |
+
batch_normalize=1
|
220 |
+
filters=256
|
221 |
+
size=3
|
222 |
+
stride=1
|
223 |
+
pad=1
|
224 |
+
activation=leaky
|
225 |
+
|
226 |
+
[shortcut]
|
227 |
+
from=-3
|
228 |
+
activation=linear
|
229 |
+
|
230 |
+
[convolutional]
|
231 |
+
batch_normalize=1
|
232 |
+
filters=128
|
233 |
+
size=1
|
234 |
+
stride=1
|
235 |
+
pad=1
|
236 |
+
activation=leaky
|
237 |
+
|
238 |
+
[convolutional]
|
239 |
+
batch_normalize=1
|
240 |
+
filters=256
|
241 |
+
size=3
|
242 |
+
stride=1
|
243 |
+
pad=1
|
244 |
+
activation=leaky
|
245 |
+
|
246 |
+
[shortcut]
|
247 |
+
from=-3
|
248 |
+
activation=linear
|
249 |
+
|
250 |
+
[convolutional]
|
251 |
+
batch_normalize=1
|
252 |
+
filters=128
|
253 |
+
size=1
|
254 |
+
stride=1
|
255 |
+
pad=1
|
256 |
+
activation=leaky
|
257 |
+
|
258 |
+
[convolutional]
|
259 |
+
batch_normalize=1
|
260 |
+
filters=256
|
261 |
+
size=3
|
262 |
+
stride=1
|
263 |
+
pad=1
|
264 |
+
activation=leaky
|
265 |
+
|
266 |
+
[shortcut]
|
267 |
+
from=-3
|
268 |
+
activation=linear
|
269 |
+
|
270 |
+
[convolutional]
|
271 |
+
batch_normalize=1
|
272 |
+
filters=128
|
273 |
+
size=1
|
274 |
+
stride=1
|
275 |
+
pad=1
|
276 |
+
activation=leaky
|
277 |
+
|
278 |
+
[convolutional]
|
279 |
+
batch_normalize=1
|
280 |
+
filters=256
|
281 |
+
size=3
|
282 |
+
stride=1
|
283 |
+
pad=1
|
284 |
+
activation=leaky
|
285 |
+
|
286 |
+
[shortcut]
|
287 |
+
from=-3
|
288 |
+
activation=linear
|
289 |
+
|
290 |
+
# Downsample
|
291 |
+
|
292 |
+
[convolutional]
|
293 |
+
batch_normalize=1
|
294 |
+
filters=512
|
295 |
+
size=3
|
296 |
+
stride=2
|
297 |
+
pad=1
|
298 |
+
activation=leaky
|
299 |
+
|
300 |
+
[convolutional]
|
301 |
+
batch_normalize=1
|
302 |
+
filters=256
|
303 |
+
size=1
|
304 |
+
stride=1
|
305 |
+
pad=1
|
306 |
+
activation=leaky
|
307 |
+
|
308 |
+
[convolutional]
|
309 |
+
batch_normalize=1
|
310 |
+
filters=512
|
311 |
+
size=3
|
312 |
+
stride=1
|
313 |
+
pad=1
|
314 |
+
activation=leaky
|
315 |
+
|
316 |
+
[shortcut]
|
317 |
+
from=-3
|
318 |
+
activation=linear
|
319 |
+
|
320 |
+
|
321 |
+
[convolutional]
|
322 |
+
batch_normalize=1
|
323 |
+
filters=256
|
324 |
+
size=1
|
325 |
+
stride=1
|
326 |
+
pad=1
|
327 |
+
activation=leaky
|
328 |
+
|
329 |
+
[convolutional]
|
330 |
+
batch_normalize=1
|
331 |
+
filters=512
|
332 |
+
size=3
|
333 |
+
stride=1
|
334 |
+
pad=1
|
335 |
+
activation=leaky
|
336 |
+
|
337 |
+
[shortcut]
|
338 |
+
from=-3
|
339 |
+
activation=linear
|
340 |
+
|
341 |
+
|
342 |
+
[convolutional]
|
343 |
+
batch_normalize=1
|
344 |
+
filters=256
|
345 |
+
size=1
|
346 |
+
stride=1
|
347 |
+
pad=1
|
348 |
+
activation=leaky
|
349 |
+
|
350 |
+
[convolutional]
|
351 |
+
batch_normalize=1
|
352 |
+
filters=512
|
353 |
+
size=3
|
354 |
+
stride=1
|
355 |
+
pad=1
|
356 |
+
activation=leaky
|
357 |
+
|
358 |
+
[shortcut]
|
359 |
+
from=-3
|
360 |
+
activation=linear
|
361 |
+
|
362 |
+
|
363 |
+
[convolutional]
|
364 |
+
batch_normalize=1
|
365 |
+
filters=256
|
366 |
+
size=1
|
367 |
+
stride=1
|
368 |
+
pad=1
|
369 |
+
activation=leaky
|
370 |
+
|
371 |
+
[convolutional]
|
372 |
+
batch_normalize=1
|
373 |
+
filters=512
|
374 |
+
size=3
|
375 |
+
stride=1
|
376 |
+
pad=1
|
377 |
+
activation=leaky
|
378 |
+
|
379 |
+
[shortcut]
|
380 |
+
from=-3
|
381 |
+
activation=linear
|
382 |
+
|
383 |
+
[convolutional]
|
384 |
+
batch_normalize=1
|
385 |
+
filters=256
|
386 |
+
size=1
|
387 |
+
stride=1
|
388 |
+
pad=1
|
389 |
+
activation=leaky
|
390 |
+
|
391 |
+
[convolutional]
|
392 |
+
batch_normalize=1
|
393 |
+
filters=512
|
394 |
+
size=3
|
395 |
+
stride=1
|
396 |
+
pad=1
|
397 |
+
activation=leaky
|
398 |
+
|
399 |
+
[shortcut]
|
400 |
+
from=-3
|
401 |
+
activation=linear
|
402 |
+
|
403 |
+
|
404 |
+
[convolutional]
|
405 |
+
batch_normalize=1
|
406 |
+
filters=256
|
407 |
+
size=1
|
408 |
+
stride=1
|
409 |
+
pad=1
|
410 |
+
activation=leaky
|
411 |
+
|
412 |
+
[convolutional]
|
413 |
+
batch_normalize=1
|
414 |
+
filters=512
|
415 |
+
size=3
|
416 |
+
stride=1
|
417 |
+
pad=1
|
418 |
+
activation=leaky
|
419 |
+
|
420 |
+
[shortcut]
|
421 |
+
from=-3
|
422 |
+
activation=linear
|
423 |
+
|
424 |
+
|
425 |
+
[convolutional]
|
426 |
+
batch_normalize=1
|
427 |
+
filters=256
|
428 |
+
size=1
|
429 |
+
stride=1
|
430 |
+
pad=1
|
431 |
+
activation=leaky
|
432 |
+
|
433 |
+
[convolutional]
|
434 |
+
batch_normalize=1
|
435 |
+
filters=512
|
436 |
+
size=3
|
437 |
+
stride=1
|
438 |
+
pad=1
|
439 |
+
activation=leaky
|
440 |
+
|
441 |
+
[shortcut]
|
442 |
+
from=-3
|
443 |
+
activation=linear
|
444 |
+
|
445 |
+
[convolutional]
|
446 |
+
batch_normalize=1
|
447 |
+
filters=256
|
448 |
+
size=1
|
449 |
+
stride=1
|
450 |
+
pad=1
|
451 |
+
activation=leaky
|
452 |
+
|
453 |
+
[convolutional]
|
454 |
+
batch_normalize=1
|
455 |
+
filters=512
|
456 |
+
size=3
|
457 |
+
stride=1
|
458 |
+
pad=1
|
459 |
+
activation=leaky
|
460 |
+
|
461 |
+
[shortcut]
|
462 |
+
from=-3
|
463 |
+
activation=linear
|
464 |
+
|
465 |
+
# Downsample
|
466 |
+
|
467 |
+
[convolutional]
|
468 |
+
batch_normalize=1
|
469 |
+
filters=1024
|
470 |
+
size=3
|
471 |
+
stride=2
|
472 |
+
pad=1
|
473 |
+
activation=leaky
|
474 |
+
|
475 |
+
[convolutional]
|
476 |
+
batch_normalize=1
|
477 |
+
filters=512
|
478 |
+
size=1
|
479 |
+
stride=1
|
480 |
+
pad=1
|
481 |
+
activation=leaky
|
482 |
+
|
483 |
+
[convolutional]
|
484 |
+
batch_normalize=1
|
485 |
+
filters=1024
|
486 |
+
size=3
|
487 |
+
stride=1
|
488 |
+
pad=1
|
489 |
+
activation=leaky
|
490 |
+
|
491 |
+
[shortcut]
|
492 |
+
from=-3
|
493 |
+
activation=linear
|
494 |
+
|
495 |
+
[convolutional]
|
496 |
+
batch_normalize=1
|
497 |
+
filters=512
|
498 |
+
size=1
|
499 |
+
stride=1
|
500 |
+
pad=1
|
501 |
+
activation=leaky
|
502 |
+
|
503 |
+
[convolutional]
|
504 |
+
batch_normalize=1
|
505 |
+
filters=1024
|
506 |
+
size=3
|
507 |
+
stride=1
|
508 |
+
pad=1
|
509 |
+
activation=leaky
|
510 |
+
|
511 |
+
[shortcut]
|
512 |
+
from=-3
|
513 |
+
activation=linear
|
514 |
+
|
515 |
+
[convolutional]
|
516 |
+
batch_normalize=1
|
517 |
+
filters=512
|
518 |
+
size=1
|
519 |
+
stride=1
|
520 |
+
pad=1
|
521 |
+
activation=leaky
|
522 |
+
|
523 |
+
[convolutional]
|
524 |
+
batch_normalize=1
|
525 |
+
filters=1024
|
526 |
+
size=3
|
527 |
+
stride=1
|
528 |
+
pad=1
|
529 |
+
activation=leaky
|
530 |
+
|
531 |
+
[shortcut]
|
532 |
+
from=-3
|
533 |
+
activation=linear
|
534 |
+
|
535 |
+
[convolutional]
|
536 |
+
batch_normalize=1
|
537 |
+
filters=512
|
538 |
+
size=1
|
539 |
+
stride=1
|
540 |
+
pad=1
|
541 |
+
activation=leaky
|
542 |
+
|
543 |
+
[convolutional]
|
544 |
+
batch_normalize=1
|
545 |
+
filters=1024
|
546 |
+
size=3
|
547 |
+
stride=1
|
548 |
+
pad=1
|
549 |
+
activation=leaky
|
550 |
+
|
551 |
+
[shortcut]
|
552 |
+
from=-3
|
553 |
+
activation=linear
|
554 |
+
|
555 |
+
[avgpool]
|
556 |
+
|
557 |
+
[convolutional]
|
558 |
+
filters=1000
|
559 |
+
size=1
|
560 |
+
stride=1
|
561 |
+
pad=1
|
562 |
+
activation=linear
|
563 |
+
|
564 |
+
[softmax]
|
565 |
+
groups=1
|
566 |
+
|
model/cfg/darknet53_448.cfg
ADDED
@@ -0,0 +1,559 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training - start training with darknet53.weights
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=8
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=448
|
11 |
+
width=448
|
12 |
+
channels=3
|
13 |
+
min_crop=448
|
14 |
+
max_crop=512
|
15 |
+
|
16 |
+
learning_rate=0.001
|
17 |
+
policy=poly
|
18 |
+
power=4
|
19 |
+
max_batches=100000
|
20 |
+
momentum=0.9
|
21 |
+
decay=0.0005
|
22 |
+
|
23 |
+
|
24 |
+
[convolutional]
|
25 |
+
batch_normalize=1
|
26 |
+
filters=32
|
27 |
+
size=3
|
28 |
+
stride=1
|
29 |
+
pad=1
|
30 |
+
activation=leaky
|
31 |
+
|
32 |
+
# Downsample
|
33 |
+
|
34 |
+
[convolutional]
|
35 |
+
batch_normalize=1
|
36 |
+
filters=64
|
37 |
+
size=3
|
38 |
+
stride=2
|
39 |
+
pad=1
|
40 |
+
activation=leaky
|
41 |
+
|
42 |
+
[convolutional]
|
43 |
+
batch_normalize=1
|
44 |
+
filters=32
|
45 |
+
size=1
|
46 |
+
stride=1
|
47 |
+
pad=1
|
48 |
+
activation=leaky
|
49 |
+
|
50 |
+
[convolutional]
|
51 |
+
batch_normalize=1
|
52 |
+
filters=64
|
53 |
+
size=3
|
54 |
+
stride=1
|
55 |
+
pad=1
|
56 |
+
activation=leaky
|
57 |
+
|
58 |
+
[shortcut]
|
59 |
+
from=-3
|
60 |
+
activation=linear
|
61 |
+
|
62 |
+
# Downsample
|
63 |
+
|
64 |
+
[convolutional]
|
65 |
+
batch_normalize=1
|
66 |
+
filters=128
|
67 |
+
size=3
|
68 |
+
stride=2
|
69 |
+
pad=1
|
70 |
+
activation=leaky
|
71 |
+
|
72 |
+
[convolutional]
|
73 |
+
batch_normalize=1
|
74 |
+
filters=64
|
75 |
+
size=1
|
76 |
+
stride=1
|
77 |
+
pad=1
|
78 |
+
activation=leaky
|
79 |
+
|
80 |
+
[convolutional]
|
81 |
+
batch_normalize=1
|
82 |
+
filters=128
|
83 |
+
size=3
|
84 |
+
stride=1
|
85 |
+
pad=1
|
86 |
+
activation=leaky
|
87 |
+
|
88 |
+
[shortcut]
|
89 |
+
from=-3
|
90 |
+
activation=linear
|
91 |
+
|
92 |
+
[convolutional]
|
93 |
+
batch_normalize=1
|
94 |
+
filters=64
|
95 |
+
size=1
|
96 |
+
stride=1
|
97 |
+
pad=1
|
98 |
+
activation=leaky
|
99 |
+
|
100 |
+
[convolutional]
|
101 |
+
batch_normalize=1
|
102 |
+
filters=128
|
103 |
+
size=3
|
104 |
+
stride=1
|
105 |
+
pad=1
|
106 |
+
activation=leaky
|
107 |
+
|
108 |
+
[shortcut]
|
109 |
+
from=-3
|
110 |
+
activation=linear
|
111 |
+
|
112 |
+
# Downsample
|
113 |
+
|
114 |
+
[convolutional]
|
115 |
+
batch_normalize=1
|
116 |
+
filters=256
|
117 |
+
size=3
|
118 |
+
stride=2
|
119 |
+
pad=1
|
120 |
+
activation=leaky
|
121 |
+
|
122 |
+
[convolutional]
|
123 |
+
batch_normalize=1
|
124 |
+
filters=128
|
125 |
+
size=1
|
126 |
+
stride=1
|
127 |
+
pad=1
|
128 |
+
activation=leaky
|
129 |
+
|
130 |
+
[convolutional]
|
131 |
+
batch_normalize=1
|
132 |
+
filters=256
|
133 |
+
size=3
|
134 |
+
stride=1
|
135 |
+
pad=1
|
136 |
+
activation=leaky
|
137 |
+
|
138 |
+
[shortcut]
|
139 |
+
from=-3
|
140 |
+
activation=linear
|
141 |
+
|
142 |
+
[convolutional]
|
143 |
+
batch_normalize=1
|
144 |
+
filters=128
|
145 |
+
size=1
|
146 |
+
stride=1
|
147 |
+
pad=1
|
148 |
+
activation=leaky
|
149 |
+
|
150 |
+
[convolutional]
|
151 |
+
batch_normalize=1
|
152 |
+
filters=256
|
153 |
+
size=3
|
154 |
+
stride=1
|
155 |
+
pad=1
|
156 |
+
activation=leaky
|
157 |
+
|
158 |
+
[shortcut]
|
159 |
+
from=-3
|
160 |
+
activation=linear
|
161 |
+
|
162 |
+
[convolutional]
|
163 |
+
batch_normalize=1
|
164 |
+
filters=128
|
165 |
+
size=1
|
166 |
+
stride=1
|
167 |
+
pad=1
|
168 |
+
activation=leaky
|
169 |
+
|
170 |
+
[convolutional]
|
171 |
+
batch_normalize=1
|
172 |
+
filters=256
|
173 |
+
size=3
|
174 |
+
stride=1
|
175 |
+
pad=1
|
176 |
+
activation=leaky
|
177 |
+
|
178 |
+
[shortcut]
|
179 |
+
from=-3
|
180 |
+
activation=linear
|
181 |
+
|
182 |
+
[convolutional]
|
183 |
+
batch_normalize=1
|
184 |
+
filters=128
|
185 |
+
size=1
|
186 |
+
stride=1
|
187 |
+
pad=1
|
188 |
+
activation=leaky
|
189 |
+
|
190 |
+
[convolutional]
|
191 |
+
batch_normalize=1
|
192 |
+
filters=256
|
193 |
+
size=3
|
194 |
+
stride=1
|
195 |
+
pad=1
|
196 |
+
activation=leaky
|
197 |
+
|
198 |
+
[shortcut]
|
199 |
+
from=-3
|
200 |
+
activation=linear
|
201 |
+
|
202 |
+
|
203 |
+
[convolutional]
|
204 |
+
batch_normalize=1
|
205 |
+
filters=128
|
206 |
+
size=1
|
207 |
+
stride=1
|
208 |
+
pad=1
|
209 |
+
activation=leaky
|
210 |
+
|
211 |
+
[convolutional]
|
212 |
+
batch_normalize=1
|
213 |
+
filters=256
|
214 |
+
size=3
|
215 |
+
stride=1
|
216 |
+
pad=1
|
217 |
+
activation=leaky
|
218 |
+
|
219 |
+
[shortcut]
|
220 |
+
from=-3
|
221 |
+
activation=linear
|
222 |
+
|
223 |
+
[convolutional]
|
224 |
+
batch_normalize=1
|
225 |
+
filters=128
|
226 |
+
size=1
|
227 |
+
stride=1
|
228 |
+
pad=1
|
229 |
+
activation=leaky
|
230 |
+
|
231 |
+
[convolutional]
|
232 |
+
batch_normalize=1
|
233 |
+
filters=256
|
234 |
+
size=3
|
235 |
+
stride=1
|
236 |
+
pad=1
|
237 |
+
activation=leaky
|
238 |
+
|
239 |
+
[shortcut]
|
240 |
+
from=-3
|
241 |
+
activation=linear
|
242 |
+
|
243 |
+
[convolutional]
|
244 |
+
batch_normalize=1
|
245 |
+
filters=128
|
246 |
+
size=1
|
247 |
+
stride=1
|
248 |
+
pad=1
|
249 |
+
activation=leaky
|
250 |
+
|
251 |
+
[convolutional]
|
252 |
+
batch_normalize=1
|
253 |
+
filters=256
|
254 |
+
size=3
|
255 |
+
stride=1
|
256 |
+
pad=1
|
257 |
+
activation=leaky
|
258 |
+
|
259 |
+
[shortcut]
|
260 |
+
from=-3
|
261 |
+
activation=linear
|
262 |
+
|
263 |
+
[convolutional]
|
264 |
+
batch_normalize=1
|
265 |
+
filters=128
|
266 |
+
size=1
|
267 |
+
stride=1
|
268 |
+
pad=1
|
269 |
+
activation=leaky
|
270 |
+
|
271 |
+
[convolutional]
|
272 |
+
batch_normalize=1
|
273 |
+
filters=256
|
274 |
+
size=3
|
275 |
+
stride=1
|
276 |
+
pad=1
|
277 |
+
activation=leaky
|
278 |
+
|
279 |
+
[shortcut]
|
280 |
+
from=-3
|
281 |
+
activation=linear
|
282 |
+
|
283 |
+
# Downsample
|
284 |
+
|
285 |
+
[convolutional]
|
286 |
+
batch_normalize=1
|
287 |
+
filters=512
|
288 |
+
size=3
|
289 |
+
stride=2
|
290 |
+
pad=1
|
291 |
+
activation=leaky
|
292 |
+
|
293 |
+
[convolutional]
|
294 |
+
batch_normalize=1
|
295 |
+
filters=256
|
296 |
+
size=1
|
297 |
+
stride=1
|
298 |
+
pad=1
|
299 |
+
activation=leaky
|
300 |
+
|
301 |
+
[convolutional]
|
302 |
+
batch_normalize=1
|
303 |
+
filters=512
|
304 |
+
size=3
|
305 |
+
stride=1
|
306 |
+
pad=1
|
307 |
+
activation=leaky
|
308 |
+
|
309 |
+
[shortcut]
|
310 |
+
from=-3
|
311 |
+
activation=linear
|
312 |
+
|
313 |
+
|
314 |
+
[convolutional]
|
315 |
+
batch_normalize=1
|
316 |
+
filters=256
|
317 |
+
size=1
|
318 |
+
stride=1
|
319 |
+
pad=1
|
320 |
+
activation=leaky
|
321 |
+
|
322 |
+
[convolutional]
|
323 |
+
batch_normalize=1
|
324 |
+
filters=512
|
325 |
+
size=3
|
326 |
+
stride=1
|
327 |
+
pad=1
|
328 |
+
activation=leaky
|
329 |
+
|
330 |
+
[shortcut]
|
331 |
+
from=-3
|
332 |
+
activation=linear
|
333 |
+
|
334 |
+
|
335 |
+
[convolutional]
|
336 |
+
batch_normalize=1
|
337 |
+
filters=256
|
338 |
+
size=1
|
339 |
+
stride=1
|
340 |
+
pad=1
|
341 |
+
activation=leaky
|
342 |
+
|
343 |
+
[convolutional]
|
344 |
+
batch_normalize=1
|
345 |
+
filters=512
|
346 |
+
size=3
|
347 |
+
stride=1
|
348 |
+
pad=1
|
349 |
+
activation=leaky
|
350 |
+
|
351 |
+
[shortcut]
|
352 |
+
from=-3
|
353 |
+
activation=linear
|
354 |
+
|
355 |
+
|
356 |
+
[convolutional]
|
357 |
+
batch_normalize=1
|
358 |
+
filters=256
|
359 |
+
size=1
|
360 |
+
stride=1
|
361 |
+
pad=1
|
362 |
+
activation=leaky
|
363 |
+
|
364 |
+
[convolutional]
|
365 |
+
batch_normalize=1
|
366 |
+
filters=512
|
367 |
+
size=3
|
368 |
+
stride=1
|
369 |
+
pad=1
|
370 |
+
activation=leaky
|
371 |
+
|
372 |
+
[shortcut]
|
373 |
+
from=-3
|
374 |
+
activation=linear
|
375 |
+
|
376 |
+
[convolutional]
|
377 |
+
batch_normalize=1
|
378 |
+
filters=256
|
379 |
+
size=1
|
380 |
+
stride=1
|
381 |
+
pad=1
|
382 |
+
activation=leaky
|
383 |
+
|
384 |
+
[convolutional]
|
385 |
+
batch_normalize=1
|
386 |
+
filters=512
|
387 |
+
size=3
|
388 |
+
stride=1
|
389 |
+
pad=1
|
390 |
+
activation=leaky
|
391 |
+
|
392 |
+
[shortcut]
|
393 |
+
from=-3
|
394 |
+
activation=linear
|
395 |
+
|
396 |
+
|
397 |
+
[convolutional]
|
398 |
+
batch_normalize=1
|
399 |
+
filters=256
|
400 |
+
size=1
|
401 |
+
stride=1
|
402 |
+
pad=1
|
403 |
+
activation=leaky
|
404 |
+
|
405 |
+
[convolutional]
|
406 |
+
batch_normalize=1
|
407 |
+
filters=512
|
408 |
+
size=3
|
409 |
+
stride=1
|
410 |
+
pad=1
|
411 |
+
activation=leaky
|
412 |
+
|
413 |
+
[shortcut]
|
414 |
+
from=-3
|
415 |
+
activation=linear
|
416 |
+
|
417 |
+
|
418 |
+
[convolutional]
|
419 |
+
batch_normalize=1
|
420 |
+
filters=256
|
421 |
+
size=1
|
422 |
+
stride=1
|
423 |
+
pad=1
|
424 |
+
activation=leaky
|
425 |
+
|
426 |
+
[convolutional]
|
427 |
+
batch_normalize=1
|
428 |
+
filters=512
|
429 |
+
size=3
|
430 |
+
stride=1
|
431 |
+
pad=1
|
432 |
+
activation=leaky
|
433 |
+
|
434 |
+
[shortcut]
|
435 |
+
from=-3
|
436 |
+
activation=linear
|
437 |
+
|
438 |
+
[convolutional]
|
439 |
+
batch_normalize=1
|
440 |
+
filters=256
|
441 |
+
size=1
|
442 |
+
stride=1
|
443 |
+
pad=1
|
444 |
+
activation=leaky
|
445 |
+
|
446 |
+
[convolutional]
|
447 |
+
batch_normalize=1
|
448 |
+
filters=512
|
449 |
+
size=3
|
450 |
+
stride=1
|
451 |
+
pad=1
|
452 |
+
activation=leaky
|
453 |
+
|
454 |
+
[shortcut]
|
455 |
+
from=-3
|
456 |
+
activation=linear
|
457 |
+
|
458 |
+
# Downsample
|
459 |
+
|
460 |
+
[convolutional]
|
461 |
+
batch_normalize=1
|
462 |
+
filters=1024
|
463 |
+
size=3
|
464 |
+
stride=2
|
465 |
+
pad=1
|
466 |
+
activation=leaky
|
467 |
+
|
468 |
+
[convolutional]
|
469 |
+
batch_normalize=1
|
470 |
+
filters=512
|
471 |
+
size=1
|
472 |
+
stride=1
|
473 |
+
pad=1
|
474 |
+
activation=leaky
|
475 |
+
|
476 |
+
[convolutional]
|
477 |
+
batch_normalize=1
|
478 |
+
filters=1024
|
479 |
+
size=3
|
480 |
+
stride=1
|
481 |
+
pad=1
|
482 |
+
activation=leaky
|
483 |
+
|
484 |
+
[shortcut]
|
485 |
+
from=-3
|
486 |
+
activation=linear
|
487 |
+
|
488 |
+
[convolutional]
|
489 |
+
batch_normalize=1
|
490 |
+
filters=512
|
491 |
+
size=1
|
492 |
+
stride=1
|
493 |
+
pad=1
|
494 |
+
activation=leaky
|
495 |
+
|
496 |
+
[convolutional]
|
497 |
+
batch_normalize=1
|
498 |
+
filters=1024
|
499 |
+
size=3
|
500 |
+
stride=1
|
501 |
+
pad=1
|
502 |
+
activation=leaky
|
503 |
+
|
504 |
+
[shortcut]
|
505 |
+
from=-3
|
506 |
+
activation=linear
|
507 |
+
|
508 |
+
[convolutional]
|
509 |
+
batch_normalize=1
|
510 |
+
filters=512
|
511 |
+
size=1
|
512 |
+
stride=1
|
513 |
+
pad=1
|
514 |
+
activation=leaky
|
515 |
+
|
516 |
+
[convolutional]
|
517 |
+
batch_normalize=1
|
518 |
+
filters=1024
|
519 |
+
size=3
|
520 |
+
stride=1
|
521 |
+
pad=1
|
522 |
+
activation=leaky
|
523 |
+
|
524 |
+
[shortcut]
|
525 |
+
from=-3
|
526 |
+
activation=linear
|
527 |
+
|
528 |
+
[convolutional]
|
529 |
+
batch_normalize=1
|
530 |
+
filters=512
|
531 |
+
size=1
|
532 |
+
stride=1
|
533 |
+
pad=1
|
534 |
+
activation=leaky
|
535 |
+
|
536 |
+
[convolutional]
|
537 |
+
batch_normalize=1
|
538 |
+
filters=1024
|
539 |
+
size=3
|
540 |
+
stride=1
|
541 |
+
pad=1
|
542 |
+
activation=leaky
|
543 |
+
|
544 |
+
[shortcut]
|
545 |
+
from=-3
|
546 |
+
activation=linear
|
547 |
+
|
548 |
+
[avgpool]
|
549 |
+
|
550 |
+
[convolutional]
|
551 |
+
filters=1000
|
552 |
+
size=1
|
553 |
+
stride=1
|
554 |
+
pad=1
|
555 |
+
activation=linear
|
556 |
+
|
557 |
+
[softmax]
|
558 |
+
groups=1
|
559 |
+
|
model/cfg/darknet9000.cfg
ADDED
@@ -0,0 +1,205 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=4
|
5 |
+
# Testing
|
6 |
+
batch = 1
|
7 |
+
subdivisions = 1
|
8 |
+
height=448
|
9 |
+
width=448
|
10 |
+
max_crop=512
|
11 |
+
channels=3
|
12 |
+
momentum=0.9
|
13 |
+
decay=0.0005
|
14 |
+
|
15 |
+
learning_rate=0.001
|
16 |
+
policy=poly
|
17 |
+
power=4
|
18 |
+
max_batches=100000
|
19 |
+
|
20 |
+
angle=7
|
21 |
+
hue=.1
|
22 |
+
saturation=.75
|
23 |
+
exposure=.75
|
24 |
+
aspect=.75
|
25 |
+
|
26 |
+
[convolutional]
|
27 |
+
batch_normalize=1
|
28 |
+
filters=32
|
29 |
+
size=3
|
30 |
+
stride=1
|
31 |
+
pad=1
|
32 |
+
activation=leaky
|
33 |
+
|
34 |
+
[maxpool]
|
35 |
+
size=2
|
36 |
+
stride=2
|
37 |
+
|
38 |
+
[convolutional]
|
39 |
+
batch_normalize=1
|
40 |
+
filters=64
|
41 |
+
size=3
|
42 |
+
stride=1
|
43 |
+
pad=1
|
44 |
+
activation=leaky
|
45 |
+
|
46 |
+
[maxpool]
|
47 |
+
size=2
|
48 |
+
stride=2
|
49 |
+
|
50 |
+
[convolutional]
|
51 |
+
batch_normalize=1
|
52 |
+
filters=128
|
53 |
+
size=3
|
54 |
+
stride=1
|
55 |
+
pad=1
|
56 |
+
activation=leaky
|
57 |
+
|
58 |
+
[convolutional]
|
59 |
+
batch_normalize=1
|
60 |
+
filters=64
|
61 |
+
size=1
|
62 |
+
stride=1
|
63 |
+
pad=1
|
64 |
+
activation=leaky
|
65 |
+
|
66 |
+
[convolutional]
|
67 |
+
batch_normalize=1
|
68 |
+
filters=128
|
69 |
+
size=3
|
70 |
+
stride=1
|
71 |
+
pad=1
|
72 |
+
activation=leaky
|
73 |
+
|
74 |
+
[maxpool]
|
75 |
+
size=2
|
76 |
+
stride=2
|
77 |
+
|
78 |
+
[convolutional]
|
79 |
+
batch_normalize=1
|
80 |
+
filters=256
|
81 |
+
size=3
|
82 |
+
stride=1
|
83 |
+
pad=1
|
84 |
+
activation=leaky
|
85 |
+
|
86 |
+
[convolutional]
|
87 |
+
batch_normalize=1
|
88 |
+
filters=128
|
89 |
+
size=1
|
90 |
+
stride=1
|
91 |
+
pad=1
|
92 |
+
activation=leaky
|
93 |
+
|
94 |
+
[convolutional]
|
95 |
+
batch_normalize=1
|
96 |
+
filters=256
|
97 |
+
size=3
|
98 |
+
stride=1
|
99 |
+
pad=1
|
100 |
+
activation=leaky
|
101 |
+
|
102 |
+
[maxpool]
|
103 |
+
size=2
|
104 |
+
stride=2
|
105 |
+
|
106 |
+
[convolutional]
|
107 |
+
batch_normalize=1
|
108 |
+
filters=512
|
109 |
+
size=3
|
110 |
+
stride=1
|
111 |
+
pad=1
|
112 |
+
activation=leaky
|
113 |
+
|
114 |
+
[convolutional]
|
115 |
+
batch_normalize=1
|
116 |
+
filters=256
|
117 |
+
size=1
|
118 |
+
stride=1
|
119 |
+
pad=1
|
120 |
+
activation=leaky
|
121 |
+
|
122 |
+
[convolutional]
|
123 |
+
batch_normalize=1
|
124 |
+
filters=512
|
125 |
+
size=3
|
126 |
+
stride=1
|
127 |
+
pad=1
|
128 |
+
activation=leaky
|
129 |
+
|
130 |
+
[convolutional]
|
131 |
+
batch_normalize=1
|
132 |
+
filters=256
|
133 |
+
size=1
|
134 |
+
stride=1
|
135 |
+
pad=1
|
136 |
+
activation=leaky
|
137 |
+
|
138 |
+
[convolutional]
|
139 |
+
batch_normalize=1
|
140 |
+
filters=512
|
141 |
+
size=3
|
142 |
+
stride=1
|
143 |
+
pad=1
|
144 |
+
activation=leaky
|
145 |
+
|
146 |
+
[maxpool]
|
147 |
+
size=2
|
148 |
+
stride=2
|
149 |
+
|
150 |
+
[convolutional]
|
151 |
+
batch_normalize=1
|
152 |
+
filters=1024
|
153 |
+
size=3
|
154 |
+
stride=1
|
155 |
+
pad=1
|
156 |
+
activation=leaky
|
157 |
+
|
158 |
+
[convolutional]
|
159 |
+
batch_normalize=1
|
160 |
+
filters=512
|
161 |
+
size=1
|
162 |
+
stride=1
|
163 |
+
pad=1
|
164 |
+
activation=leaky
|
165 |
+
|
166 |
+
[convolutional]
|
167 |
+
batch_normalize=1
|
168 |
+
filters=1024
|
169 |
+
size=3
|
170 |
+
stride=1
|
171 |
+
pad=1
|
172 |
+
activation=leaky
|
173 |
+
|
174 |
+
[convolutional]
|
175 |
+
batch_normalize=1
|
176 |
+
filters=512
|
177 |
+
size=1
|
178 |
+
stride=1
|
179 |
+
pad=1
|
180 |
+
activation=leaky
|
181 |
+
|
182 |
+
[convolutional]
|
183 |
+
batch_normalize=1
|
184 |
+
filters=1024
|
185 |
+
size=3
|
186 |
+
stride=1
|
187 |
+
pad=1
|
188 |
+
activation=leaky
|
189 |
+
|
190 |
+
[convolutional]
|
191 |
+
filters=9418
|
192 |
+
size=1
|
193 |
+
stride=1
|
194 |
+
pad=1
|
195 |
+
activation=linear
|
196 |
+
|
197 |
+
[avgpool]
|
198 |
+
|
199 |
+
[softmax]
|
200 |
+
groups=1
|
201 |
+
tree=data/9k.tree
|
202 |
+
|
203 |
+
[cost]
|
204 |
+
type=masked
|
205 |
+
|
model/cfg/densenet201.cfg
ADDED
@@ -0,0 +1,1951 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=4
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
max_crop=448
|
13 |
+
channels=3
|
14 |
+
momentum=0.9
|
15 |
+
decay=0.0005
|
16 |
+
|
17 |
+
burn_in=1000
|
18 |
+
learning_rate=0.1
|
19 |
+
policy=poly
|
20 |
+
power=4
|
21 |
+
max_batches=1600000
|
22 |
+
|
23 |
+
angle=7
|
24 |
+
hue=.1
|
25 |
+
saturation=.75
|
26 |
+
exposure=.75
|
27 |
+
aspect=.75
|
28 |
+
|
29 |
+
[convolutional]
|
30 |
+
batch_normalize=1
|
31 |
+
filters=64
|
32 |
+
size=7
|
33 |
+
stride=2
|
34 |
+
pad=1
|
35 |
+
activation=leaky
|
36 |
+
|
37 |
+
[maxpool]
|
38 |
+
size=2
|
39 |
+
stride=2
|
40 |
+
|
41 |
+
[convolutional]
|
42 |
+
batch_normalize=1
|
43 |
+
filters=128
|
44 |
+
size=1
|
45 |
+
stride=1
|
46 |
+
pad=1
|
47 |
+
activation=leaky
|
48 |
+
|
49 |
+
[convolutional]
|
50 |
+
batch_normalize=1
|
51 |
+
filters=32
|
52 |
+
size=3
|
53 |
+
stride=1
|
54 |
+
pad=1
|
55 |
+
activation=leaky
|
56 |
+
|
57 |
+
[route]
|
58 |
+
layers=-1,-3
|
59 |
+
|
60 |
+
[convolutional]
|
61 |
+
batch_normalize=1
|
62 |
+
filters=128
|
63 |
+
size=1
|
64 |
+
stride=1
|
65 |
+
pad=1
|
66 |
+
activation=leaky
|
67 |
+
|
68 |
+
[convolutional]
|
69 |
+
batch_normalize=1
|
70 |
+
filters=32
|
71 |
+
size=3
|
72 |
+
stride=1
|
73 |
+
pad=1
|
74 |
+
activation=leaky
|
75 |
+
|
76 |
+
[route]
|
77 |
+
layers=-1,-3
|
78 |
+
|
79 |
+
[convolutional]
|
80 |
+
batch_normalize=1
|
81 |
+
filters=128
|
82 |
+
size=1
|
83 |
+
stride=1
|
84 |
+
pad=1
|
85 |
+
activation=leaky
|
86 |
+
|
87 |
+
[convolutional]
|
88 |
+
batch_normalize=1
|
89 |
+
filters=32
|
90 |
+
size=3
|
91 |
+
stride=1
|
92 |
+
pad=1
|
93 |
+
activation=leaky
|
94 |
+
|
95 |
+
[route]
|
96 |
+
layers=-1,-3
|
97 |
+
|
98 |
+
[convolutional]
|
99 |
+
batch_normalize=1
|
100 |
+
filters=128
|
101 |
+
size=1
|
102 |
+
stride=1
|
103 |
+
pad=1
|
104 |
+
activation=leaky
|
105 |
+
|
106 |
+
[convolutional]
|
107 |
+
batch_normalize=1
|
108 |
+
filters=32
|
109 |
+
size=3
|
110 |
+
stride=1
|
111 |
+
pad=1
|
112 |
+
activation=leaky
|
113 |
+
|
114 |
+
[route]
|
115 |
+
layers=-1,-3
|
116 |
+
|
117 |
+
[convolutional]
|
118 |
+
batch_normalize=1
|
119 |
+
filters=128
|
120 |
+
size=1
|
121 |
+
stride=1
|
122 |
+
pad=1
|
123 |
+
activation=leaky
|
124 |
+
|
125 |
+
[convolutional]
|
126 |
+
batch_normalize=1
|
127 |
+
filters=32
|
128 |
+
size=3
|
129 |
+
stride=1
|
130 |
+
pad=1
|
131 |
+
activation=leaky
|
132 |
+
|
133 |
+
[route]
|
134 |
+
layers=-1,-3
|
135 |
+
|
136 |
+
[convolutional]
|
137 |
+
batch_normalize=1
|
138 |
+
filters=128
|
139 |
+
size=1
|
140 |
+
stride=1
|
141 |
+
pad=1
|
142 |
+
activation=leaky
|
143 |
+
|
144 |
+
[convolutional]
|
145 |
+
batch_normalize=1
|
146 |
+
filters=32
|
147 |
+
size=3
|
148 |
+
stride=1
|
149 |
+
pad=1
|
150 |
+
activation=leaky
|
151 |
+
|
152 |
+
[route]
|
153 |
+
layers=-1,-3
|
154 |
+
|
155 |
+
[convolutional]
|
156 |
+
batch_normalize=1
|
157 |
+
filters=128
|
158 |
+
size=1
|
159 |
+
stride=1
|
160 |
+
pad=1
|
161 |
+
activation=leaky
|
162 |
+
|
163 |
+
[maxpool]
|
164 |
+
size=2
|
165 |
+
stride=2
|
166 |
+
|
167 |
+
[convolutional]
|
168 |
+
batch_normalize=1
|
169 |
+
filters=128
|
170 |
+
size=1
|
171 |
+
stride=1
|
172 |
+
pad=1
|
173 |
+
activation=leaky
|
174 |
+
|
175 |
+
[convolutional]
|
176 |
+
batch_normalize=1
|
177 |
+
filters=32
|
178 |
+
size=3
|
179 |
+
stride=1
|
180 |
+
pad=1
|
181 |
+
activation=leaky
|
182 |
+
|
183 |
+
[route]
|
184 |
+
layers=-1,-3
|
185 |
+
|
186 |
+
[convolutional]
|
187 |
+
batch_normalize=1
|
188 |
+
filters=128
|
189 |
+
size=1
|
190 |
+
stride=1
|
191 |
+
pad=1
|
192 |
+
activation=leaky
|
193 |
+
|
194 |
+
[convolutional]
|
195 |
+
batch_normalize=1
|
196 |
+
filters=32
|
197 |
+
size=3
|
198 |
+
stride=1
|
199 |
+
pad=1
|
200 |
+
activation=leaky
|
201 |
+
|
202 |
+
[route]
|
203 |
+
layers=-1,-3
|
204 |
+
|
205 |
+
[convolutional]
|
206 |
+
batch_normalize=1
|
207 |
+
filters=128
|
208 |
+
size=1
|
209 |
+
stride=1
|
210 |
+
pad=1
|
211 |
+
activation=leaky
|
212 |
+
|
213 |
+
[convolutional]
|
214 |
+
batch_normalize=1
|
215 |
+
filters=32
|
216 |
+
size=3
|
217 |
+
stride=1
|
218 |
+
pad=1
|
219 |
+
activation=leaky
|
220 |
+
|
221 |
+
[route]
|
222 |
+
layers=-1,-3
|
223 |
+
|
224 |
+
[convolutional]
|
225 |
+
batch_normalize=1
|
226 |
+
filters=128
|
227 |
+
size=1
|
228 |
+
stride=1
|
229 |
+
pad=1
|
230 |
+
activation=leaky
|
231 |
+
|
232 |
+
[convolutional]
|
233 |
+
batch_normalize=1
|
234 |
+
filters=32
|
235 |
+
size=3
|
236 |
+
stride=1
|
237 |
+
pad=1
|
238 |
+
activation=leaky
|
239 |
+
|
240 |
+
[route]
|
241 |
+
layers=-1,-3
|
242 |
+
|
243 |
+
[convolutional]
|
244 |
+
batch_normalize=1
|
245 |
+
filters=128
|
246 |
+
size=1
|
247 |
+
stride=1
|
248 |
+
pad=1
|
249 |
+
activation=leaky
|
250 |
+
|
251 |
+
[convolutional]
|
252 |
+
batch_normalize=1
|
253 |
+
filters=32
|
254 |
+
size=3
|
255 |
+
stride=1
|
256 |
+
pad=1
|
257 |
+
activation=leaky
|
258 |
+
|
259 |
+
[route]
|
260 |
+
layers=-1,-3
|
261 |
+
|
262 |
+
[convolutional]
|
263 |
+
batch_normalize=1
|
264 |
+
filters=128
|
265 |
+
size=1
|
266 |
+
stride=1
|
267 |
+
pad=1
|
268 |
+
activation=leaky
|
269 |
+
|
270 |
+
[convolutional]
|
271 |
+
batch_normalize=1
|
272 |
+
filters=32
|
273 |
+
size=3
|
274 |
+
stride=1
|
275 |
+
pad=1
|
276 |
+
activation=leaky
|
277 |
+
|
278 |
+
[route]
|
279 |
+
layers=-1,-3
|
280 |
+
|
281 |
+
[convolutional]
|
282 |
+
batch_normalize=1
|
283 |
+
filters=128
|
284 |
+
size=1
|
285 |
+
stride=1
|
286 |
+
pad=1
|
287 |
+
activation=leaky
|
288 |
+
|
289 |
+
[convolutional]
|
290 |
+
batch_normalize=1
|
291 |
+
filters=32
|
292 |
+
size=3
|
293 |
+
stride=1
|
294 |
+
pad=1
|
295 |
+
activation=leaky
|
296 |
+
|
297 |
+
[route]
|
298 |
+
layers=-1,-3
|
299 |
+
|
300 |
+
[convolutional]
|
301 |
+
batch_normalize=1
|
302 |
+
filters=128
|
303 |
+
size=1
|
304 |
+
stride=1
|
305 |
+
pad=1
|
306 |
+
activation=leaky
|
307 |
+
|
308 |
+
[convolutional]
|
309 |
+
batch_normalize=1
|
310 |
+
filters=32
|
311 |
+
size=3
|
312 |
+
stride=1
|
313 |
+
pad=1
|
314 |
+
activation=leaky
|
315 |
+
|
316 |
+
[route]
|
317 |
+
layers=-1,-3
|
318 |
+
|
319 |
+
[convolutional]
|
320 |
+
batch_normalize=1
|
321 |
+
filters=128
|
322 |
+
size=1
|
323 |
+
stride=1
|
324 |
+
pad=1
|
325 |
+
activation=leaky
|
326 |
+
|
327 |
+
[convolutional]
|
328 |
+
batch_normalize=1
|
329 |
+
filters=32
|
330 |
+
size=3
|
331 |
+
stride=1
|
332 |
+
pad=1
|
333 |
+
activation=leaky
|
334 |
+
|
335 |
+
[route]
|
336 |
+
layers=-1,-3
|
337 |
+
|
338 |
+
[convolutional]
|
339 |
+
batch_normalize=1
|
340 |
+
filters=128
|
341 |
+
size=1
|
342 |
+
stride=1
|
343 |
+
pad=1
|
344 |
+
activation=leaky
|
345 |
+
|
346 |
+
[convolutional]
|
347 |
+
batch_normalize=1
|
348 |
+
filters=32
|
349 |
+
size=3
|
350 |
+
stride=1
|
351 |
+
pad=1
|
352 |
+
activation=leaky
|
353 |
+
|
354 |
+
[route]
|
355 |
+
layers=-1,-3
|
356 |
+
|
357 |
+
[convolutional]
|
358 |
+
batch_normalize=1
|
359 |
+
filters=128
|
360 |
+
size=1
|
361 |
+
stride=1
|
362 |
+
pad=1
|
363 |
+
activation=leaky
|
364 |
+
|
365 |
+
[convolutional]
|
366 |
+
batch_normalize=1
|
367 |
+
filters=32
|
368 |
+
size=3
|
369 |
+
stride=1
|
370 |
+
pad=1
|
371 |
+
activation=leaky
|
372 |
+
|
373 |
+
[route]
|
374 |
+
layers=-1,-3
|
375 |
+
|
376 |
+
[convolutional]
|
377 |
+
batch_normalize=1
|
378 |
+
filters=128
|
379 |
+
size=1
|
380 |
+
stride=1
|
381 |
+
pad=1
|
382 |
+
activation=leaky
|
383 |
+
|
384 |
+
[convolutional]
|
385 |
+
batch_normalize=1
|
386 |
+
filters=32
|
387 |
+
size=3
|
388 |
+
stride=1
|
389 |
+
pad=1
|
390 |
+
activation=leaky
|
391 |
+
|
392 |
+
[route]
|
393 |
+
layers=-1,-3
|
394 |
+
|
395 |
+
[convolutional]
|
396 |
+
batch_normalize=1
|
397 |
+
filters=256
|
398 |
+
size=1
|
399 |
+
stride=1
|
400 |
+
pad=1
|
401 |
+
activation=leaky
|
402 |
+
|
403 |
+
[maxpool]
|
404 |
+
size=2
|
405 |
+
stride=2
|
406 |
+
|
407 |
+
[convolutional]
|
408 |
+
batch_normalize=1
|
409 |
+
filters=128
|
410 |
+
size=1
|
411 |
+
stride=1
|
412 |
+
pad=1
|
413 |
+
activation=leaky
|
414 |
+
|
415 |
+
[convolutional]
|
416 |
+
batch_normalize=1
|
417 |
+
filters=32
|
418 |
+
size=3
|
419 |
+
stride=1
|
420 |
+
pad=1
|
421 |
+
activation=leaky
|
422 |
+
|
423 |
+
[route]
|
424 |
+
layers=-1,-3
|
425 |
+
|
426 |
+
[convolutional]
|
427 |
+
batch_normalize=1
|
428 |
+
filters=128
|
429 |
+
size=1
|
430 |
+
stride=1
|
431 |
+
pad=1
|
432 |
+
activation=leaky
|
433 |
+
|
434 |
+
[convolutional]
|
435 |
+
batch_normalize=1
|
436 |
+
filters=32
|
437 |
+
size=3
|
438 |
+
stride=1
|
439 |
+
pad=1
|
440 |
+
activation=leaky
|
441 |
+
|
442 |
+
[route]
|
443 |
+
layers=-1,-3
|
444 |
+
|
445 |
+
[convolutional]
|
446 |
+
batch_normalize=1
|
447 |
+
filters=128
|
448 |
+
size=1
|
449 |
+
stride=1
|
450 |
+
pad=1
|
451 |
+
activation=leaky
|
452 |
+
|
453 |
+
[convolutional]
|
454 |
+
batch_normalize=1
|
455 |
+
filters=32
|
456 |
+
size=3
|
457 |
+
stride=1
|
458 |
+
pad=1
|
459 |
+
activation=leaky
|
460 |
+
|
461 |
+
[route]
|
462 |
+
layers=-1,-3
|
463 |
+
|
464 |
+
[convolutional]
|
465 |
+
batch_normalize=1
|
466 |
+
filters=128
|
467 |
+
size=1
|
468 |
+
stride=1
|
469 |
+
pad=1
|
470 |
+
activation=leaky
|
471 |
+
|
472 |
+
[convolutional]
|
473 |
+
batch_normalize=1
|
474 |
+
filters=32
|
475 |
+
size=3
|
476 |
+
stride=1
|
477 |
+
pad=1
|
478 |
+
activation=leaky
|
479 |
+
|
480 |
+
[route]
|
481 |
+
layers=-1,-3
|
482 |
+
|
483 |
+
[convolutional]
|
484 |
+
batch_normalize=1
|
485 |
+
filters=128
|
486 |
+
size=1
|
487 |
+
stride=1
|
488 |
+
pad=1
|
489 |
+
activation=leaky
|
490 |
+
|
491 |
+
[convolutional]
|
492 |
+
batch_normalize=1
|
493 |
+
filters=32
|
494 |
+
size=3
|
495 |
+
stride=1
|
496 |
+
pad=1
|
497 |
+
activation=leaky
|
498 |
+
|
499 |
+
[route]
|
500 |
+
layers=-1,-3
|
501 |
+
|
502 |
+
[convolutional]
|
503 |
+
batch_normalize=1
|
504 |
+
filters=128
|
505 |
+
size=1
|
506 |
+
stride=1
|
507 |
+
pad=1
|
508 |
+
activation=leaky
|
509 |
+
|
510 |
+
[convolutional]
|
511 |
+
batch_normalize=1
|
512 |
+
filters=32
|
513 |
+
size=3
|
514 |
+
stride=1
|
515 |
+
pad=1
|
516 |
+
activation=leaky
|
517 |
+
|
518 |
+
[route]
|
519 |
+
layers=-1,-3
|
520 |
+
|
521 |
+
[convolutional]
|
522 |
+
batch_normalize=1
|
523 |
+
filters=128
|
524 |
+
size=1
|
525 |
+
stride=1
|
526 |
+
pad=1
|
527 |
+
activation=leaky
|
528 |
+
|
529 |
+
[convolutional]
|
530 |
+
batch_normalize=1
|
531 |
+
filters=32
|
532 |
+
size=3
|
533 |
+
stride=1
|
534 |
+
pad=1
|
535 |
+
activation=leaky
|
536 |
+
|
537 |
+
[route]
|
538 |
+
layers=-1,-3
|
539 |
+
|
540 |
+
[convolutional]
|
541 |
+
batch_normalize=1
|
542 |
+
filters=128
|
543 |
+
size=1
|
544 |
+
stride=1
|
545 |
+
pad=1
|
546 |
+
activation=leaky
|
547 |
+
|
548 |
+
[convolutional]
|
549 |
+
batch_normalize=1
|
550 |
+
filters=32
|
551 |
+
size=3
|
552 |
+
stride=1
|
553 |
+
pad=1
|
554 |
+
activation=leaky
|
555 |
+
|
556 |
+
[route]
|
557 |
+
layers=-1,-3
|
558 |
+
|
559 |
+
[convolutional]
|
560 |
+
batch_normalize=1
|
561 |
+
filters=128
|
562 |
+
size=1
|
563 |
+
stride=1
|
564 |
+
pad=1
|
565 |
+
activation=leaky
|
566 |
+
|
567 |
+
[convolutional]
|
568 |
+
batch_normalize=1
|
569 |
+
filters=32
|
570 |
+
size=3
|
571 |
+
stride=1
|
572 |
+
pad=1
|
573 |
+
activation=leaky
|
574 |
+
|
575 |
+
[route]
|
576 |
+
layers=-1,-3
|
577 |
+
|
578 |
+
[convolutional]
|
579 |
+
batch_normalize=1
|
580 |
+
filters=128
|
581 |
+
size=1
|
582 |
+
stride=1
|
583 |
+
pad=1
|
584 |
+
activation=leaky
|
585 |
+
|
586 |
+
[convolutional]
|
587 |
+
batch_normalize=1
|
588 |
+
filters=32
|
589 |
+
size=3
|
590 |
+
stride=1
|
591 |
+
pad=1
|
592 |
+
activation=leaky
|
593 |
+
|
594 |
+
[route]
|
595 |
+
layers=-1,-3
|
596 |
+
|
597 |
+
[convolutional]
|
598 |
+
batch_normalize=1
|
599 |
+
filters=128
|
600 |
+
size=1
|
601 |
+
stride=1
|
602 |
+
pad=1
|
603 |
+
activation=leaky
|
604 |
+
|
605 |
+
[convolutional]
|
606 |
+
batch_normalize=1
|
607 |
+
filters=32
|
608 |
+
size=3
|
609 |
+
stride=1
|
610 |
+
pad=1
|
611 |
+
activation=leaky
|
612 |
+
|
613 |
+
[route]
|
614 |
+
layers=-1,-3
|
615 |
+
|
616 |
+
[convolutional]
|
617 |
+
batch_normalize=1
|
618 |
+
filters=128
|
619 |
+
size=1
|
620 |
+
stride=1
|
621 |
+
pad=1
|
622 |
+
activation=leaky
|
623 |
+
|
624 |
+
[convolutional]
|
625 |
+
batch_normalize=1
|
626 |
+
filters=32
|
627 |
+
size=3
|
628 |
+
stride=1
|
629 |
+
pad=1
|
630 |
+
activation=leaky
|
631 |
+
|
632 |
+
[route]
|
633 |
+
layers=-1,-3
|
634 |
+
|
635 |
+
[convolutional]
|
636 |
+
batch_normalize=1
|
637 |
+
filters=128
|
638 |
+
size=1
|
639 |
+
stride=1
|
640 |
+
pad=1
|
641 |
+
activation=leaky
|
642 |
+
|
643 |
+
[convolutional]
|
644 |
+
batch_normalize=1
|
645 |
+
filters=32
|
646 |
+
size=3
|
647 |
+
stride=1
|
648 |
+
pad=1
|
649 |
+
activation=leaky
|
650 |
+
|
651 |
+
[route]
|
652 |
+
layers=-1,-3
|
653 |
+
|
654 |
+
[convolutional]
|
655 |
+
batch_normalize=1
|
656 |
+
filters=128
|
657 |
+
size=1
|
658 |
+
stride=1
|
659 |
+
pad=1
|
660 |
+
activation=leaky
|
661 |
+
|
662 |
+
[convolutional]
|
663 |
+
batch_normalize=1
|
664 |
+
filters=32
|
665 |
+
size=3
|
666 |
+
stride=1
|
667 |
+
pad=1
|
668 |
+
activation=leaky
|
669 |
+
|
670 |
+
[route]
|
671 |
+
layers=-1,-3
|
672 |
+
|
673 |
+
[convolutional]
|
674 |
+
batch_normalize=1
|
675 |
+
filters=128
|
676 |
+
size=1
|
677 |
+
stride=1
|
678 |
+
pad=1
|
679 |
+
activation=leaky
|
680 |
+
|
681 |
+
[convolutional]
|
682 |
+
batch_normalize=1
|
683 |
+
filters=32
|
684 |
+
size=3
|
685 |
+
stride=1
|
686 |
+
pad=1
|
687 |
+
activation=leaky
|
688 |
+
|
689 |
+
[route]
|
690 |
+
layers=-1,-3
|
691 |
+
|
692 |
+
[convolutional]
|
693 |
+
batch_normalize=1
|
694 |
+
filters=128
|
695 |
+
size=1
|
696 |
+
stride=1
|
697 |
+
pad=1
|
698 |
+
activation=leaky
|
699 |
+
|
700 |
+
[convolutional]
|
701 |
+
batch_normalize=1
|
702 |
+
filters=32
|
703 |
+
size=3
|
704 |
+
stride=1
|
705 |
+
pad=1
|
706 |
+
activation=leaky
|
707 |
+
|
708 |
+
[route]
|
709 |
+
layers=-1,-3
|
710 |
+
|
711 |
+
[convolutional]
|
712 |
+
batch_normalize=1
|
713 |
+
filters=128
|
714 |
+
size=1
|
715 |
+
stride=1
|
716 |
+
pad=1
|
717 |
+
activation=leaky
|
718 |
+
|
719 |
+
[convolutional]
|
720 |
+
batch_normalize=1
|
721 |
+
filters=32
|
722 |
+
size=3
|
723 |
+
stride=1
|
724 |
+
pad=1
|
725 |
+
activation=leaky
|
726 |
+
|
727 |
+
[route]
|
728 |
+
layers=-1,-3
|
729 |
+
|
730 |
+
[convolutional]
|
731 |
+
batch_normalize=1
|
732 |
+
filters=128
|
733 |
+
size=1
|
734 |
+
stride=1
|
735 |
+
pad=1
|
736 |
+
activation=leaky
|
737 |
+
|
738 |
+
[convolutional]
|
739 |
+
batch_normalize=1
|
740 |
+
filters=32
|
741 |
+
size=3
|
742 |
+
stride=1
|
743 |
+
pad=1
|
744 |
+
activation=leaky
|
745 |
+
|
746 |
+
[route]
|
747 |
+
layers=-1,-3
|
748 |
+
|
749 |
+
[convolutional]
|
750 |
+
batch_normalize=1
|
751 |
+
filters=128
|
752 |
+
size=1
|
753 |
+
stride=1
|
754 |
+
pad=1
|
755 |
+
activation=leaky
|
756 |
+
|
757 |
+
[convolutional]
|
758 |
+
batch_normalize=1
|
759 |
+
filters=32
|
760 |
+
size=3
|
761 |
+
stride=1
|
762 |
+
pad=1
|
763 |
+
activation=leaky
|
764 |
+
|
765 |
+
[route]
|
766 |
+
layers=-1,-3
|
767 |
+
|
768 |
+
[convolutional]
|
769 |
+
batch_normalize=1
|
770 |
+
filters=128
|
771 |
+
size=1
|
772 |
+
stride=1
|
773 |
+
pad=1
|
774 |
+
activation=leaky
|
775 |
+
|
776 |
+
[convolutional]
|
777 |
+
batch_normalize=1
|
778 |
+
filters=32
|
779 |
+
size=3
|
780 |
+
stride=1
|
781 |
+
pad=1
|
782 |
+
activation=leaky
|
783 |
+
|
784 |
+
[route]
|
785 |
+
layers=-1,-3
|
786 |
+
|
787 |
+
[convolutional]
|
788 |
+
batch_normalize=1
|
789 |
+
filters=128
|
790 |
+
size=1
|
791 |
+
stride=1
|
792 |
+
pad=1
|
793 |
+
activation=leaky
|
794 |
+
|
795 |
+
[convolutional]
|
796 |
+
batch_normalize=1
|
797 |
+
filters=32
|
798 |
+
size=3
|
799 |
+
stride=1
|
800 |
+
pad=1
|
801 |
+
activation=leaky
|
802 |
+
|
803 |
+
[route]
|
804 |
+
layers=-1,-3
|
805 |
+
|
806 |
+
[convolutional]
|
807 |
+
batch_normalize=1
|
808 |
+
filters=128
|
809 |
+
size=1
|
810 |
+
stride=1
|
811 |
+
pad=1
|
812 |
+
activation=leaky
|
813 |
+
|
814 |
+
[convolutional]
|
815 |
+
batch_normalize=1
|
816 |
+
filters=32
|
817 |
+
size=3
|
818 |
+
stride=1
|
819 |
+
pad=1
|
820 |
+
activation=leaky
|
821 |
+
|
822 |
+
[route]
|
823 |
+
layers=-1,-3
|
824 |
+
|
825 |
+
[convolutional]
|
826 |
+
batch_normalize=1
|
827 |
+
filters=128
|
828 |
+
size=1
|
829 |
+
stride=1
|
830 |
+
pad=1
|
831 |
+
activation=leaky
|
832 |
+
|
833 |
+
[convolutional]
|
834 |
+
batch_normalize=1
|
835 |
+
filters=32
|
836 |
+
size=3
|
837 |
+
stride=1
|
838 |
+
pad=1
|
839 |
+
activation=leaky
|
840 |
+
|
841 |
+
[route]
|
842 |
+
layers=-1,-3
|
843 |
+
|
844 |
+
[convolutional]
|
845 |
+
batch_normalize=1
|
846 |
+
filters=128
|
847 |
+
size=1
|
848 |
+
stride=1
|
849 |
+
pad=1
|
850 |
+
activation=leaky
|
851 |
+
|
852 |
+
[convolutional]
|
853 |
+
batch_normalize=1
|
854 |
+
filters=32
|
855 |
+
size=3
|
856 |
+
stride=1
|
857 |
+
pad=1
|
858 |
+
activation=leaky
|
859 |
+
|
860 |
+
[route]
|
861 |
+
layers=-1,-3
|
862 |
+
|
863 |
+
[convolutional]
|
864 |
+
batch_normalize=1
|
865 |
+
filters=128
|
866 |
+
size=1
|
867 |
+
stride=1
|
868 |
+
pad=1
|
869 |
+
activation=leaky
|
870 |
+
|
871 |
+
[convolutional]
|
872 |
+
batch_normalize=1
|
873 |
+
filters=32
|
874 |
+
size=3
|
875 |
+
stride=1
|
876 |
+
pad=1
|
877 |
+
activation=leaky
|
878 |
+
|
879 |
+
[route]
|
880 |
+
layers=-1,-3
|
881 |
+
|
882 |
+
[convolutional]
|
883 |
+
batch_normalize=1
|
884 |
+
filters=128
|
885 |
+
size=1
|
886 |
+
stride=1
|
887 |
+
pad=1
|
888 |
+
activation=leaky
|
889 |
+
|
890 |
+
[convolutional]
|
891 |
+
batch_normalize=1
|
892 |
+
filters=32
|
893 |
+
size=3
|
894 |
+
stride=1
|
895 |
+
pad=1
|
896 |
+
activation=leaky
|
897 |
+
|
898 |
+
[route]
|
899 |
+
layers=-1,-3
|
900 |
+
|
901 |
+
[convolutional]
|
902 |
+
batch_normalize=1
|
903 |
+
filters=128
|
904 |
+
size=1
|
905 |
+
stride=1
|
906 |
+
pad=1
|
907 |
+
activation=leaky
|
908 |
+
|
909 |
+
[convolutional]
|
910 |
+
batch_normalize=1
|
911 |
+
filters=32
|
912 |
+
size=3
|
913 |
+
stride=1
|
914 |
+
pad=1
|
915 |
+
activation=leaky
|
916 |
+
|
917 |
+
[route]
|
918 |
+
layers=-1,-3
|
919 |
+
|
920 |
+
[convolutional]
|
921 |
+
batch_normalize=1
|
922 |
+
filters=128
|
923 |
+
size=1
|
924 |
+
stride=1
|
925 |
+
pad=1
|
926 |
+
activation=leaky
|
927 |
+
|
928 |
+
[convolutional]
|
929 |
+
batch_normalize=1
|
930 |
+
filters=32
|
931 |
+
size=3
|
932 |
+
stride=1
|
933 |
+
pad=1
|
934 |
+
activation=leaky
|
935 |
+
|
936 |
+
[route]
|
937 |
+
layers=-1,-3
|
938 |
+
|
939 |
+
[convolutional]
|
940 |
+
batch_normalize=1
|
941 |
+
filters=128
|
942 |
+
size=1
|
943 |
+
stride=1
|
944 |
+
pad=1
|
945 |
+
activation=leaky
|
946 |
+
|
947 |
+
[convolutional]
|
948 |
+
batch_normalize=1
|
949 |
+
filters=32
|
950 |
+
size=3
|
951 |
+
stride=1
|
952 |
+
pad=1
|
953 |
+
activation=leaky
|
954 |
+
|
955 |
+
[route]
|
956 |
+
layers=-1,-3
|
957 |
+
|
958 |
+
[convolutional]
|
959 |
+
batch_normalize=1
|
960 |
+
filters=128
|
961 |
+
size=1
|
962 |
+
stride=1
|
963 |
+
pad=1
|
964 |
+
activation=leaky
|
965 |
+
|
966 |
+
[convolutional]
|
967 |
+
batch_normalize=1
|
968 |
+
filters=32
|
969 |
+
size=3
|
970 |
+
stride=1
|
971 |
+
pad=1
|
972 |
+
activation=leaky
|
973 |
+
|
974 |
+
[route]
|
975 |
+
layers=-1,-3
|
976 |
+
|
977 |
+
[convolutional]
|
978 |
+
batch_normalize=1
|
979 |
+
filters=128
|
980 |
+
size=1
|
981 |
+
stride=1
|
982 |
+
pad=1
|
983 |
+
activation=leaky
|
984 |
+
|
985 |
+
[convolutional]
|
986 |
+
batch_normalize=1
|
987 |
+
filters=32
|
988 |
+
size=3
|
989 |
+
stride=1
|
990 |
+
pad=1
|
991 |
+
activation=leaky
|
992 |
+
|
993 |
+
[route]
|
994 |
+
layers=-1,-3
|
995 |
+
|
996 |
+
[convolutional]
|
997 |
+
batch_normalize=1
|
998 |
+
filters=128
|
999 |
+
size=1
|
1000 |
+
stride=1
|
1001 |
+
pad=1
|
1002 |
+
activation=leaky
|
1003 |
+
|
1004 |
+
[convolutional]
|
1005 |
+
batch_normalize=1
|
1006 |
+
filters=32
|
1007 |
+
size=3
|
1008 |
+
stride=1
|
1009 |
+
pad=1
|
1010 |
+
activation=leaky
|
1011 |
+
|
1012 |
+
[route]
|
1013 |
+
layers=-1,-3
|
1014 |
+
|
1015 |
+
[convolutional]
|
1016 |
+
batch_normalize=1
|
1017 |
+
filters=128
|
1018 |
+
size=1
|
1019 |
+
stride=1
|
1020 |
+
pad=1
|
1021 |
+
activation=leaky
|
1022 |
+
|
1023 |
+
[convolutional]
|
1024 |
+
batch_normalize=1
|
1025 |
+
filters=32
|
1026 |
+
size=3
|
1027 |
+
stride=1
|
1028 |
+
pad=1
|
1029 |
+
activation=leaky
|
1030 |
+
|
1031 |
+
[route]
|
1032 |
+
layers=-1,-3
|
1033 |
+
|
1034 |
+
[convolutional]
|
1035 |
+
batch_normalize=1
|
1036 |
+
filters=128
|
1037 |
+
size=1
|
1038 |
+
stride=1
|
1039 |
+
pad=1
|
1040 |
+
activation=leaky
|
1041 |
+
|
1042 |
+
[convolutional]
|
1043 |
+
batch_normalize=1
|
1044 |
+
filters=32
|
1045 |
+
size=3
|
1046 |
+
stride=1
|
1047 |
+
pad=1
|
1048 |
+
activation=leaky
|
1049 |
+
|
1050 |
+
[route]
|
1051 |
+
layers=-1,-3
|
1052 |
+
|
1053 |
+
[convolutional]
|
1054 |
+
batch_normalize=1
|
1055 |
+
filters=128
|
1056 |
+
size=1
|
1057 |
+
stride=1
|
1058 |
+
pad=1
|
1059 |
+
activation=leaky
|
1060 |
+
|
1061 |
+
[convolutional]
|
1062 |
+
batch_normalize=1
|
1063 |
+
filters=32
|
1064 |
+
size=3
|
1065 |
+
stride=1
|
1066 |
+
pad=1
|
1067 |
+
activation=leaky
|
1068 |
+
|
1069 |
+
[route]
|
1070 |
+
layers=-1,-3
|
1071 |
+
|
1072 |
+
[convolutional]
|
1073 |
+
batch_normalize=1
|
1074 |
+
filters=128
|
1075 |
+
size=1
|
1076 |
+
stride=1
|
1077 |
+
pad=1
|
1078 |
+
activation=leaky
|
1079 |
+
|
1080 |
+
[convolutional]
|
1081 |
+
batch_normalize=1
|
1082 |
+
filters=32
|
1083 |
+
size=3
|
1084 |
+
stride=1
|
1085 |
+
pad=1
|
1086 |
+
activation=leaky
|
1087 |
+
|
1088 |
+
[route]
|
1089 |
+
layers=-1,-3
|
1090 |
+
|
1091 |
+
[convolutional]
|
1092 |
+
batch_normalize=1
|
1093 |
+
filters=128
|
1094 |
+
size=1
|
1095 |
+
stride=1
|
1096 |
+
pad=1
|
1097 |
+
activation=leaky
|
1098 |
+
|
1099 |
+
[convolutional]
|
1100 |
+
batch_normalize=1
|
1101 |
+
filters=32
|
1102 |
+
size=3
|
1103 |
+
stride=1
|
1104 |
+
pad=1
|
1105 |
+
activation=leaky
|
1106 |
+
|
1107 |
+
[route]
|
1108 |
+
layers=-1,-3
|
1109 |
+
|
1110 |
+
[convolutional]
|
1111 |
+
batch_normalize=1
|
1112 |
+
filters=128
|
1113 |
+
size=1
|
1114 |
+
stride=1
|
1115 |
+
pad=1
|
1116 |
+
activation=leaky
|
1117 |
+
|
1118 |
+
[convolutional]
|
1119 |
+
batch_normalize=1
|
1120 |
+
filters=32
|
1121 |
+
size=3
|
1122 |
+
stride=1
|
1123 |
+
pad=1
|
1124 |
+
activation=leaky
|
1125 |
+
|
1126 |
+
[route]
|
1127 |
+
layers=-1,-3
|
1128 |
+
|
1129 |
+
[convolutional]
|
1130 |
+
batch_normalize=1
|
1131 |
+
filters=128
|
1132 |
+
size=1
|
1133 |
+
stride=1
|
1134 |
+
pad=1
|
1135 |
+
activation=leaky
|
1136 |
+
|
1137 |
+
[convolutional]
|
1138 |
+
batch_normalize=1
|
1139 |
+
filters=32
|
1140 |
+
size=3
|
1141 |
+
stride=1
|
1142 |
+
pad=1
|
1143 |
+
activation=leaky
|
1144 |
+
|
1145 |
+
[route]
|
1146 |
+
layers=-1,-3
|
1147 |
+
|
1148 |
+
[convolutional]
|
1149 |
+
batch_normalize=1
|
1150 |
+
filters=128
|
1151 |
+
size=1
|
1152 |
+
stride=1
|
1153 |
+
pad=1
|
1154 |
+
activation=leaky
|
1155 |
+
|
1156 |
+
[convolutional]
|
1157 |
+
batch_normalize=1
|
1158 |
+
filters=32
|
1159 |
+
size=3
|
1160 |
+
stride=1
|
1161 |
+
pad=1
|
1162 |
+
activation=leaky
|
1163 |
+
|
1164 |
+
[route]
|
1165 |
+
layers=-1,-3
|
1166 |
+
|
1167 |
+
[convolutional]
|
1168 |
+
batch_normalize=1
|
1169 |
+
filters=128
|
1170 |
+
size=1
|
1171 |
+
stride=1
|
1172 |
+
pad=1
|
1173 |
+
activation=leaky
|
1174 |
+
|
1175 |
+
[convolutional]
|
1176 |
+
batch_normalize=1
|
1177 |
+
filters=32
|
1178 |
+
size=3
|
1179 |
+
stride=1
|
1180 |
+
pad=1
|
1181 |
+
activation=leaky
|
1182 |
+
|
1183 |
+
[route]
|
1184 |
+
layers=-1,-3
|
1185 |
+
|
1186 |
+
[convolutional]
|
1187 |
+
batch_normalize=1
|
1188 |
+
filters=128
|
1189 |
+
size=1
|
1190 |
+
stride=1
|
1191 |
+
pad=1
|
1192 |
+
activation=leaky
|
1193 |
+
|
1194 |
+
[convolutional]
|
1195 |
+
batch_normalize=1
|
1196 |
+
filters=32
|
1197 |
+
size=3
|
1198 |
+
stride=1
|
1199 |
+
pad=1
|
1200 |
+
activation=leaky
|
1201 |
+
|
1202 |
+
[route]
|
1203 |
+
layers=-1,-3
|
1204 |
+
|
1205 |
+
[convolutional]
|
1206 |
+
batch_normalize=1
|
1207 |
+
filters=128
|
1208 |
+
size=1
|
1209 |
+
stride=1
|
1210 |
+
pad=1
|
1211 |
+
activation=leaky
|
1212 |
+
|
1213 |
+
[convolutional]
|
1214 |
+
batch_normalize=1
|
1215 |
+
filters=32
|
1216 |
+
size=3
|
1217 |
+
stride=1
|
1218 |
+
pad=1
|
1219 |
+
activation=leaky
|
1220 |
+
|
1221 |
+
[route]
|
1222 |
+
layers=-1,-3
|
1223 |
+
|
1224 |
+
[convolutional]
|
1225 |
+
batch_normalize=1
|
1226 |
+
filters=128
|
1227 |
+
size=1
|
1228 |
+
stride=1
|
1229 |
+
pad=1
|
1230 |
+
activation=leaky
|
1231 |
+
|
1232 |
+
[convolutional]
|
1233 |
+
batch_normalize=1
|
1234 |
+
filters=32
|
1235 |
+
size=3
|
1236 |
+
stride=1
|
1237 |
+
pad=1
|
1238 |
+
activation=leaky
|
1239 |
+
|
1240 |
+
[route]
|
1241 |
+
layers=-1,-3
|
1242 |
+
|
1243 |
+
[convolutional]
|
1244 |
+
batch_normalize=1
|
1245 |
+
filters=128
|
1246 |
+
size=1
|
1247 |
+
stride=1
|
1248 |
+
pad=1
|
1249 |
+
activation=leaky
|
1250 |
+
|
1251 |
+
[convolutional]
|
1252 |
+
batch_normalize=1
|
1253 |
+
filters=32
|
1254 |
+
size=3
|
1255 |
+
stride=1
|
1256 |
+
pad=1
|
1257 |
+
activation=leaky
|
1258 |
+
|
1259 |
+
[route]
|
1260 |
+
layers=-1,-3
|
1261 |
+
|
1262 |
+
[convolutional]
|
1263 |
+
batch_normalize=1
|
1264 |
+
filters=128
|
1265 |
+
size=1
|
1266 |
+
stride=1
|
1267 |
+
pad=1
|
1268 |
+
activation=leaky
|
1269 |
+
|
1270 |
+
[convolutional]
|
1271 |
+
batch_normalize=1
|
1272 |
+
filters=32
|
1273 |
+
size=3
|
1274 |
+
stride=1
|
1275 |
+
pad=1
|
1276 |
+
activation=leaky
|
1277 |
+
|
1278 |
+
[route]
|
1279 |
+
layers=-1,-3
|
1280 |
+
|
1281 |
+
[convolutional]
|
1282 |
+
batch_normalize=1
|
1283 |
+
filters=128
|
1284 |
+
size=1
|
1285 |
+
stride=1
|
1286 |
+
pad=1
|
1287 |
+
activation=leaky
|
1288 |
+
|
1289 |
+
[convolutional]
|
1290 |
+
batch_normalize=1
|
1291 |
+
filters=32
|
1292 |
+
size=3
|
1293 |
+
stride=1
|
1294 |
+
pad=1
|
1295 |
+
activation=leaky
|
1296 |
+
|
1297 |
+
[route]
|
1298 |
+
layers=-1,-3
|
1299 |
+
|
1300 |
+
[convolutional]
|
1301 |
+
batch_normalize=1
|
1302 |
+
filters=128
|
1303 |
+
size=1
|
1304 |
+
stride=1
|
1305 |
+
pad=1
|
1306 |
+
activation=leaky
|
1307 |
+
|
1308 |
+
[convolutional]
|
1309 |
+
batch_normalize=1
|
1310 |
+
filters=32
|
1311 |
+
size=3
|
1312 |
+
stride=1
|
1313 |
+
pad=1
|
1314 |
+
activation=leaky
|
1315 |
+
|
1316 |
+
[route]
|
1317 |
+
layers=-1,-3
|
1318 |
+
|
1319 |
+
[convolutional]
|
1320 |
+
batch_normalize=1
|
1321 |
+
filters=512
|
1322 |
+
size=1
|
1323 |
+
stride=1
|
1324 |
+
pad=1
|
1325 |
+
activation=leaky
|
1326 |
+
|
1327 |
+
[maxpool]
|
1328 |
+
size=2
|
1329 |
+
stride=2
|
1330 |
+
|
1331 |
+
[convolutional]
|
1332 |
+
batch_normalize=1
|
1333 |
+
filters=128
|
1334 |
+
size=1
|
1335 |
+
stride=1
|
1336 |
+
pad=1
|
1337 |
+
activation=leaky
|
1338 |
+
|
1339 |
+
[convolutional]
|
1340 |
+
batch_normalize=1
|
1341 |
+
filters=32
|
1342 |
+
size=3
|
1343 |
+
stride=1
|
1344 |
+
pad=1
|
1345 |
+
activation=leaky
|
1346 |
+
|
1347 |
+
[route]
|
1348 |
+
layers=-1,-3
|
1349 |
+
|
1350 |
+
[convolutional]
|
1351 |
+
batch_normalize=1
|
1352 |
+
filters=128
|
1353 |
+
size=1
|
1354 |
+
stride=1
|
1355 |
+
pad=1
|
1356 |
+
activation=leaky
|
1357 |
+
|
1358 |
+
[convolutional]
|
1359 |
+
batch_normalize=1
|
1360 |
+
filters=32
|
1361 |
+
size=3
|
1362 |
+
stride=1
|
1363 |
+
pad=1
|
1364 |
+
activation=leaky
|
1365 |
+
|
1366 |
+
[route]
|
1367 |
+
layers=-1,-3
|
1368 |
+
|
1369 |
+
[convolutional]
|
1370 |
+
batch_normalize=1
|
1371 |
+
filters=128
|
1372 |
+
size=1
|
1373 |
+
stride=1
|
1374 |
+
pad=1
|
1375 |
+
activation=leaky
|
1376 |
+
|
1377 |
+
[convolutional]
|
1378 |
+
batch_normalize=1
|
1379 |
+
filters=32
|
1380 |
+
size=3
|
1381 |
+
stride=1
|
1382 |
+
pad=1
|
1383 |
+
activation=leaky
|
1384 |
+
|
1385 |
+
[route]
|
1386 |
+
layers=-1,-3
|
1387 |
+
|
1388 |
+
[convolutional]
|
1389 |
+
batch_normalize=1
|
1390 |
+
filters=128
|
1391 |
+
size=1
|
1392 |
+
stride=1
|
1393 |
+
pad=1
|
1394 |
+
activation=leaky
|
1395 |
+
|
1396 |
+
[convolutional]
|
1397 |
+
batch_normalize=1
|
1398 |
+
filters=32
|
1399 |
+
size=3
|
1400 |
+
stride=1
|
1401 |
+
pad=1
|
1402 |
+
activation=leaky
|
1403 |
+
|
1404 |
+
[route]
|
1405 |
+
layers=-1,-3
|
1406 |
+
|
1407 |
+
[convolutional]
|
1408 |
+
batch_normalize=1
|
1409 |
+
filters=128
|
1410 |
+
size=1
|
1411 |
+
stride=1
|
1412 |
+
pad=1
|
1413 |
+
activation=leaky
|
1414 |
+
|
1415 |
+
[convolutional]
|
1416 |
+
batch_normalize=1
|
1417 |
+
filters=32
|
1418 |
+
size=3
|
1419 |
+
stride=1
|
1420 |
+
pad=1
|
1421 |
+
activation=leaky
|
1422 |
+
|
1423 |
+
[route]
|
1424 |
+
layers=-1,-3
|
1425 |
+
|
1426 |
+
[convolutional]
|
1427 |
+
batch_normalize=1
|
1428 |
+
filters=128
|
1429 |
+
size=1
|
1430 |
+
stride=1
|
1431 |
+
pad=1
|
1432 |
+
activation=leaky
|
1433 |
+
|
1434 |
+
[convolutional]
|
1435 |
+
batch_normalize=1
|
1436 |
+
filters=32
|
1437 |
+
size=3
|
1438 |
+
stride=1
|
1439 |
+
pad=1
|
1440 |
+
activation=leaky
|
1441 |
+
|
1442 |
+
[route]
|
1443 |
+
layers=-1,-3
|
1444 |
+
|
1445 |
+
[convolutional]
|
1446 |
+
batch_normalize=1
|
1447 |
+
filters=128
|
1448 |
+
size=1
|
1449 |
+
stride=1
|
1450 |
+
pad=1
|
1451 |
+
activation=leaky
|
1452 |
+
|
1453 |
+
[convolutional]
|
1454 |
+
batch_normalize=1
|
1455 |
+
filters=32
|
1456 |
+
size=3
|
1457 |
+
stride=1
|
1458 |
+
pad=1
|
1459 |
+
activation=leaky
|
1460 |
+
|
1461 |
+
[route]
|
1462 |
+
layers=-1,-3
|
1463 |
+
|
1464 |
+
[convolutional]
|
1465 |
+
batch_normalize=1
|
1466 |
+
filters=128
|
1467 |
+
size=1
|
1468 |
+
stride=1
|
1469 |
+
pad=1
|
1470 |
+
activation=leaky
|
1471 |
+
|
1472 |
+
[convolutional]
|
1473 |
+
batch_normalize=1
|
1474 |
+
filters=32
|
1475 |
+
size=3
|
1476 |
+
stride=1
|
1477 |
+
pad=1
|
1478 |
+
activation=leaky
|
1479 |
+
|
1480 |
+
[route]
|
1481 |
+
layers=-1,-3
|
1482 |
+
|
1483 |
+
[convolutional]
|
1484 |
+
batch_normalize=1
|
1485 |
+
filters=128
|
1486 |
+
size=1
|
1487 |
+
stride=1
|
1488 |
+
pad=1
|
1489 |
+
activation=leaky
|
1490 |
+
|
1491 |
+
[convolutional]
|
1492 |
+
batch_normalize=1
|
1493 |
+
filters=32
|
1494 |
+
size=3
|
1495 |
+
stride=1
|
1496 |
+
pad=1
|
1497 |
+
activation=leaky
|
1498 |
+
|
1499 |
+
[route]
|
1500 |
+
layers=-1,-3
|
1501 |
+
|
1502 |
+
[convolutional]
|
1503 |
+
batch_normalize=1
|
1504 |
+
filters=128
|
1505 |
+
size=1
|
1506 |
+
stride=1
|
1507 |
+
pad=1
|
1508 |
+
activation=leaky
|
1509 |
+
|
1510 |
+
[convolutional]
|
1511 |
+
batch_normalize=1
|
1512 |
+
filters=32
|
1513 |
+
size=3
|
1514 |
+
stride=1
|
1515 |
+
pad=1
|
1516 |
+
activation=leaky
|
1517 |
+
|
1518 |
+
[route]
|
1519 |
+
layers=-1,-3
|
1520 |
+
|
1521 |
+
[convolutional]
|
1522 |
+
batch_normalize=1
|
1523 |
+
filters=128
|
1524 |
+
size=1
|
1525 |
+
stride=1
|
1526 |
+
pad=1
|
1527 |
+
activation=leaky
|
1528 |
+
|
1529 |
+
[convolutional]
|
1530 |
+
batch_normalize=1
|
1531 |
+
filters=32
|
1532 |
+
size=3
|
1533 |
+
stride=1
|
1534 |
+
pad=1
|
1535 |
+
activation=leaky
|
1536 |
+
|
1537 |
+
[route]
|
1538 |
+
layers=-1,-3
|
1539 |
+
|
1540 |
+
[convolutional]
|
1541 |
+
batch_normalize=1
|
1542 |
+
filters=128
|
1543 |
+
size=1
|
1544 |
+
stride=1
|
1545 |
+
pad=1
|
1546 |
+
activation=leaky
|
1547 |
+
|
1548 |
+
[convolutional]
|
1549 |
+
batch_normalize=1
|
1550 |
+
filters=32
|
1551 |
+
size=3
|
1552 |
+
stride=1
|
1553 |
+
pad=1
|
1554 |
+
activation=leaky
|
1555 |
+
|
1556 |
+
[route]
|
1557 |
+
layers=-1,-3
|
1558 |
+
|
1559 |
+
[convolutional]
|
1560 |
+
batch_normalize=1
|
1561 |
+
filters=128
|
1562 |
+
size=1
|
1563 |
+
stride=1
|
1564 |
+
pad=1
|
1565 |
+
activation=leaky
|
1566 |
+
|
1567 |
+
[convolutional]
|
1568 |
+
batch_normalize=1
|
1569 |
+
filters=32
|
1570 |
+
size=3
|
1571 |
+
stride=1
|
1572 |
+
pad=1
|
1573 |
+
activation=leaky
|
1574 |
+
|
1575 |
+
[route]
|
1576 |
+
layers=-1,-3
|
1577 |
+
|
1578 |
+
[convolutional]
|
1579 |
+
batch_normalize=1
|
1580 |
+
filters=128
|
1581 |
+
size=1
|
1582 |
+
stride=1
|
1583 |
+
pad=1
|
1584 |
+
activation=leaky
|
1585 |
+
|
1586 |
+
[convolutional]
|
1587 |
+
batch_normalize=1
|
1588 |
+
filters=32
|
1589 |
+
size=3
|
1590 |
+
stride=1
|
1591 |
+
pad=1
|
1592 |
+
activation=leaky
|
1593 |
+
|
1594 |
+
[route]
|
1595 |
+
layers=-1,-3
|
1596 |
+
|
1597 |
+
[convolutional]
|
1598 |
+
batch_normalize=1
|
1599 |
+
filters=128
|
1600 |
+
size=1
|
1601 |
+
stride=1
|
1602 |
+
pad=1
|
1603 |
+
activation=leaky
|
1604 |
+
|
1605 |
+
[convolutional]
|
1606 |
+
batch_normalize=1
|
1607 |
+
filters=32
|
1608 |
+
size=3
|
1609 |
+
stride=1
|
1610 |
+
pad=1
|
1611 |
+
activation=leaky
|
1612 |
+
|
1613 |
+
[route]
|
1614 |
+
layers=-1,-3
|
1615 |
+
|
1616 |
+
[convolutional]
|
1617 |
+
batch_normalize=1
|
1618 |
+
filters=128
|
1619 |
+
size=1
|
1620 |
+
stride=1
|
1621 |
+
pad=1
|
1622 |
+
activation=leaky
|
1623 |
+
|
1624 |
+
[convolutional]
|
1625 |
+
batch_normalize=1
|
1626 |
+
filters=32
|
1627 |
+
size=3
|
1628 |
+
stride=1
|
1629 |
+
pad=1
|
1630 |
+
activation=leaky
|
1631 |
+
|
1632 |
+
[route]
|
1633 |
+
layers=-1,-3
|
1634 |
+
|
1635 |
+
[convolutional]
|
1636 |
+
batch_normalize=1
|
1637 |
+
filters=128
|
1638 |
+
size=1
|
1639 |
+
stride=1
|
1640 |
+
pad=1
|
1641 |
+
activation=leaky
|
1642 |
+
|
1643 |
+
[convolutional]
|
1644 |
+
batch_normalize=1
|
1645 |
+
filters=32
|
1646 |
+
size=3
|
1647 |
+
stride=1
|
1648 |
+
pad=1
|
1649 |
+
activation=leaky
|
1650 |
+
|
1651 |
+
[route]
|
1652 |
+
layers=-1,-3
|
1653 |
+
|
1654 |
+
[convolutional]
|
1655 |
+
batch_normalize=1
|
1656 |
+
filters=128
|
1657 |
+
size=1
|
1658 |
+
stride=1
|
1659 |
+
pad=1
|
1660 |
+
activation=leaky
|
1661 |
+
|
1662 |
+
[convolutional]
|
1663 |
+
batch_normalize=1
|
1664 |
+
filters=32
|
1665 |
+
size=3
|
1666 |
+
stride=1
|
1667 |
+
pad=1
|
1668 |
+
activation=leaky
|
1669 |
+
|
1670 |
+
[route]
|
1671 |
+
layers=-1,-3
|
1672 |
+
|
1673 |
+
[convolutional]
|
1674 |
+
batch_normalize=1
|
1675 |
+
filters=128
|
1676 |
+
size=1
|
1677 |
+
stride=1
|
1678 |
+
pad=1
|
1679 |
+
activation=leaky
|
1680 |
+
|
1681 |
+
[convolutional]
|
1682 |
+
batch_normalize=1
|
1683 |
+
filters=32
|
1684 |
+
size=3
|
1685 |
+
stride=1
|
1686 |
+
pad=1
|
1687 |
+
activation=leaky
|
1688 |
+
|
1689 |
+
[route]
|
1690 |
+
layers=-1,-3
|
1691 |
+
|
1692 |
+
[convolutional]
|
1693 |
+
batch_normalize=1
|
1694 |
+
filters=128
|
1695 |
+
size=1
|
1696 |
+
stride=1
|
1697 |
+
pad=1
|
1698 |
+
activation=leaky
|
1699 |
+
|
1700 |
+
[convolutional]
|
1701 |
+
batch_normalize=1
|
1702 |
+
filters=32
|
1703 |
+
size=3
|
1704 |
+
stride=1
|
1705 |
+
pad=1
|
1706 |
+
activation=leaky
|
1707 |
+
|
1708 |
+
[route]
|
1709 |
+
layers=-1,-3
|
1710 |
+
|
1711 |
+
[convolutional]
|
1712 |
+
batch_normalize=1
|
1713 |
+
filters=128
|
1714 |
+
size=1
|
1715 |
+
stride=1
|
1716 |
+
pad=1
|
1717 |
+
activation=leaky
|
1718 |
+
|
1719 |
+
[convolutional]
|
1720 |
+
batch_normalize=1
|
1721 |
+
filters=32
|
1722 |
+
size=3
|
1723 |
+
stride=1
|
1724 |
+
pad=1
|
1725 |
+
activation=leaky
|
1726 |
+
|
1727 |
+
[route]
|
1728 |
+
layers=-1,-3
|
1729 |
+
|
1730 |
+
[convolutional]
|
1731 |
+
batch_normalize=1
|
1732 |
+
filters=128
|
1733 |
+
size=1
|
1734 |
+
stride=1
|
1735 |
+
pad=1
|
1736 |
+
activation=leaky
|
1737 |
+
|
1738 |
+
[convolutional]
|
1739 |
+
batch_normalize=1
|
1740 |
+
filters=32
|
1741 |
+
size=3
|
1742 |
+
stride=1
|
1743 |
+
pad=1
|
1744 |
+
activation=leaky
|
1745 |
+
|
1746 |
+
[route]
|
1747 |
+
layers=-1,-3
|
1748 |
+
|
1749 |
+
[convolutional]
|
1750 |
+
batch_normalize=1
|
1751 |
+
filters=128
|
1752 |
+
size=1
|
1753 |
+
stride=1
|
1754 |
+
pad=1
|
1755 |
+
activation=leaky
|
1756 |
+
|
1757 |
+
[convolutional]
|
1758 |
+
batch_normalize=1
|
1759 |
+
filters=32
|
1760 |
+
size=3
|
1761 |
+
stride=1
|
1762 |
+
pad=1
|
1763 |
+
activation=leaky
|
1764 |
+
|
1765 |
+
[route]
|
1766 |
+
layers=-1,-3
|
1767 |
+
|
1768 |
+
[convolutional]
|
1769 |
+
batch_normalize=1
|
1770 |
+
filters=128
|
1771 |
+
size=1
|
1772 |
+
stride=1
|
1773 |
+
pad=1
|
1774 |
+
activation=leaky
|
1775 |
+
|
1776 |
+
[convolutional]
|
1777 |
+
batch_normalize=1
|
1778 |
+
filters=32
|
1779 |
+
size=3
|
1780 |
+
stride=1
|
1781 |
+
pad=1
|
1782 |
+
activation=leaky
|
1783 |
+
|
1784 |
+
[route]
|
1785 |
+
layers=-1,-3
|
1786 |
+
|
1787 |
+
[convolutional]
|
1788 |
+
batch_normalize=1
|
1789 |
+
filters=128
|
1790 |
+
size=1
|
1791 |
+
stride=1
|
1792 |
+
pad=1
|
1793 |
+
activation=leaky
|
1794 |
+
|
1795 |
+
[convolutional]
|
1796 |
+
batch_normalize=1
|
1797 |
+
filters=32
|
1798 |
+
size=3
|
1799 |
+
stride=1
|
1800 |
+
pad=1
|
1801 |
+
activation=leaky
|
1802 |
+
|
1803 |
+
[route]
|
1804 |
+
layers=-1,-3
|
1805 |
+
|
1806 |
+
[convolutional]
|
1807 |
+
batch_normalize=1
|
1808 |
+
filters=128
|
1809 |
+
size=1
|
1810 |
+
stride=1
|
1811 |
+
pad=1
|
1812 |
+
activation=leaky
|
1813 |
+
|
1814 |
+
[convolutional]
|
1815 |
+
batch_normalize=1
|
1816 |
+
filters=32
|
1817 |
+
size=3
|
1818 |
+
stride=1
|
1819 |
+
pad=1
|
1820 |
+
activation=leaky
|
1821 |
+
|
1822 |
+
[route]
|
1823 |
+
layers=-1,-3
|
1824 |
+
|
1825 |
+
[convolutional]
|
1826 |
+
batch_normalize=1
|
1827 |
+
filters=128
|
1828 |
+
size=1
|
1829 |
+
stride=1
|
1830 |
+
pad=1
|
1831 |
+
activation=leaky
|
1832 |
+
|
1833 |
+
[convolutional]
|
1834 |
+
batch_normalize=1
|
1835 |
+
filters=32
|
1836 |
+
size=3
|
1837 |
+
stride=1
|
1838 |
+
pad=1
|
1839 |
+
activation=leaky
|
1840 |
+
|
1841 |
+
[route]
|
1842 |
+
layers=-1,-3
|
1843 |
+
|
1844 |
+
[convolutional]
|
1845 |
+
batch_normalize=1
|
1846 |
+
filters=128
|
1847 |
+
size=1
|
1848 |
+
stride=1
|
1849 |
+
pad=1
|
1850 |
+
activation=leaky
|
1851 |
+
|
1852 |
+
[convolutional]
|
1853 |
+
batch_normalize=1
|
1854 |
+
filters=32
|
1855 |
+
size=3
|
1856 |
+
stride=1
|
1857 |
+
pad=1
|
1858 |
+
activation=leaky
|
1859 |
+
|
1860 |
+
[route]
|
1861 |
+
layers=-1,-3
|
1862 |
+
|
1863 |
+
[convolutional]
|
1864 |
+
batch_normalize=1
|
1865 |
+
filters=128
|
1866 |
+
size=1
|
1867 |
+
stride=1
|
1868 |
+
pad=1
|
1869 |
+
activation=leaky
|
1870 |
+
|
1871 |
+
[convolutional]
|
1872 |
+
batch_normalize=1
|
1873 |
+
filters=32
|
1874 |
+
size=3
|
1875 |
+
stride=1
|
1876 |
+
pad=1
|
1877 |
+
activation=leaky
|
1878 |
+
|
1879 |
+
[route]
|
1880 |
+
layers=-1,-3
|
1881 |
+
|
1882 |
+
[convolutional]
|
1883 |
+
batch_normalize=1
|
1884 |
+
filters=128
|
1885 |
+
size=1
|
1886 |
+
stride=1
|
1887 |
+
pad=1
|
1888 |
+
activation=leaky
|
1889 |
+
|
1890 |
+
[convolutional]
|
1891 |
+
batch_normalize=1
|
1892 |
+
filters=32
|
1893 |
+
size=3
|
1894 |
+
stride=1
|
1895 |
+
pad=1
|
1896 |
+
activation=leaky
|
1897 |
+
|
1898 |
+
[route]
|
1899 |
+
layers=-1,-3
|
1900 |
+
|
1901 |
+
[convolutional]
|
1902 |
+
batch_normalize=1
|
1903 |
+
filters=128
|
1904 |
+
size=1
|
1905 |
+
stride=1
|
1906 |
+
pad=1
|
1907 |
+
activation=leaky
|
1908 |
+
|
1909 |
+
[convolutional]
|
1910 |
+
batch_normalize=1
|
1911 |
+
filters=32
|
1912 |
+
size=3
|
1913 |
+
stride=1
|
1914 |
+
pad=1
|
1915 |
+
activation=leaky
|
1916 |
+
|
1917 |
+
[route]
|
1918 |
+
layers=-1,-3
|
1919 |
+
|
1920 |
+
[convolutional]
|
1921 |
+
batch_normalize=1
|
1922 |
+
filters=128
|
1923 |
+
size=1
|
1924 |
+
stride=1
|
1925 |
+
pad=1
|
1926 |
+
activation=leaky
|
1927 |
+
|
1928 |
+
[convolutional]
|
1929 |
+
batch_normalize=1
|
1930 |
+
filters=32
|
1931 |
+
size=3
|
1932 |
+
stride=1
|
1933 |
+
pad=1
|
1934 |
+
activation=leaky
|
1935 |
+
|
1936 |
+
[route]
|
1937 |
+
layers=-1,-3
|
1938 |
+
|
1939 |
+
|
1940 |
+
[convolutional]
|
1941 |
+
filters=1000
|
1942 |
+
size=1
|
1943 |
+
stride=1
|
1944 |
+
pad=1
|
1945 |
+
activation=linear
|
1946 |
+
|
1947 |
+
[avgpool]
|
1948 |
+
|
1949 |
+
[softmax]
|
1950 |
+
groups=1
|
1951 |
+
|
model/cfg/extraction.cfg
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=4
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=224
|
11 |
+
width=224
|
12 |
+
max_crop=320
|
13 |
+
channels=3
|
14 |
+
momentum=0.9
|
15 |
+
decay=0.0005
|
16 |
+
|
17 |
+
learning_rate=0.1
|
18 |
+
policy=poly
|
19 |
+
power=4
|
20 |
+
max_batches=1600000
|
21 |
+
|
22 |
+
[convolutional]
|
23 |
+
batch_normalize=1
|
24 |
+
filters=64
|
25 |
+
size=7
|
26 |
+
stride=2
|
27 |
+
pad=1
|
28 |
+
activation=leaky
|
29 |
+
|
30 |
+
[maxpool]
|
31 |
+
size=2
|
32 |
+
stride=2
|
33 |
+
|
34 |
+
[convolutional]
|
35 |
+
batch_normalize=1
|
36 |
+
filters=192
|
37 |
+
size=3
|
38 |
+
stride=1
|
39 |
+
pad=1
|
40 |
+
activation=leaky
|
41 |
+
|
42 |
+
[maxpool]
|
43 |
+
size=2
|
44 |
+
stride=2
|
45 |
+
|
46 |
+
[convolutional]
|
47 |
+
batch_normalize=1
|
48 |
+
filters=128
|
49 |
+
size=1
|
50 |
+
stride=1
|
51 |
+
pad=1
|
52 |
+
activation=leaky
|
53 |
+
|
54 |
+
[convolutional]
|
55 |
+
batch_normalize=1
|
56 |
+
filters=256
|
57 |
+
size=3
|
58 |
+
stride=1
|
59 |
+
pad=1
|
60 |
+
activation=leaky
|
61 |
+
|
62 |
+
[convolutional]
|
63 |
+
batch_normalize=1
|
64 |
+
filters=256
|
65 |
+
size=1
|
66 |
+
stride=1
|
67 |
+
pad=1
|
68 |
+
activation=leaky
|
69 |
+
|
70 |
+
[convolutional]
|
71 |
+
batch_normalize=1
|
72 |
+
filters=512
|
73 |
+
size=3
|
74 |
+
stride=1
|
75 |
+
pad=1
|
76 |
+
activation=leaky
|
77 |
+
|
78 |
+
[maxpool]
|
79 |
+
size=2
|
80 |
+
stride=2
|
81 |
+
|
82 |
+
[convolutional]
|
83 |
+
batch_normalize=1
|
84 |
+
filters=256
|
85 |
+
size=1
|
86 |
+
stride=1
|
87 |
+
pad=1
|
88 |
+
activation=leaky
|
89 |
+
|
90 |
+
[convolutional]
|
91 |
+
batch_normalize=1
|
92 |
+
filters=512
|
93 |
+
size=3
|
94 |
+
stride=1
|
95 |
+
pad=1
|
96 |
+
activation=leaky
|
97 |
+
|
98 |
+
[convolutional]
|
99 |
+
batch_normalize=1
|
100 |
+
filters=256
|
101 |
+
size=1
|
102 |
+
stride=1
|
103 |
+
pad=1
|
104 |
+
activation=leaky
|
105 |
+
|
106 |
+
[convolutional]
|
107 |
+
batch_normalize=1
|
108 |
+
filters=512
|
109 |
+
size=3
|
110 |
+
stride=1
|
111 |
+
pad=1
|
112 |
+
activation=leaky
|
113 |
+
|
114 |
+
[convolutional]
|
115 |
+
batch_normalize=1
|
116 |
+
filters=256
|
117 |
+
size=1
|
118 |
+
stride=1
|
119 |
+
pad=1
|
120 |
+
activation=leaky
|
121 |
+
|
122 |
+
[convolutional]
|
123 |
+
batch_normalize=1
|
124 |
+
filters=512
|
125 |
+
size=3
|
126 |
+
stride=1
|
127 |
+
pad=1
|
128 |
+
activation=leaky
|
129 |
+
|
130 |
+
[convolutional]
|
131 |
+
batch_normalize=1
|
132 |
+
filters=256
|
133 |
+
size=1
|
134 |
+
stride=1
|
135 |
+
pad=1
|
136 |
+
activation=leaky
|
137 |
+
|
138 |
+
[convolutional]
|
139 |
+
batch_normalize=1
|
140 |
+
filters=512
|
141 |
+
size=3
|
142 |
+
stride=1
|
143 |
+
pad=1
|
144 |
+
activation=leaky
|
145 |
+
|
146 |
+
[convolutional]
|
147 |
+
batch_normalize=1
|
148 |
+
filters=512
|
149 |
+
size=1
|
150 |
+
stride=1
|
151 |
+
pad=1
|
152 |
+
activation=leaky
|
153 |
+
|
154 |
+
[convolutional]
|
155 |
+
batch_normalize=1
|
156 |
+
filters=1024
|
157 |
+
size=3
|
158 |
+
stride=1
|
159 |
+
pad=1
|
160 |
+
activation=leaky
|
161 |
+
|
162 |
+
[maxpool]
|
163 |
+
size=2
|
164 |
+
stride=2
|
165 |
+
|
166 |
+
[convolutional]
|
167 |
+
batch_normalize=1
|
168 |
+
filters=512
|
169 |
+
size=1
|
170 |
+
stride=1
|
171 |
+
pad=1
|
172 |
+
activation=leaky
|
173 |
+
|
174 |
+
[convolutional]
|
175 |
+
batch_normalize=1
|
176 |
+
filters=1024
|
177 |
+
size=3
|
178 |
+
stride=1
|
179 |
+
pad=1
|
180 |
+
activation=leaky
|
181 |
+
|
182 |
+
[convolutional]
|
183 |
+
batch_normalize=1
|
184 |
+
filters=512
|
185 |
+
size=1
|
186 |
+
stride=1
|
187 |
+
pad=1
|
188 |
+
activation=leaky
|
189 |
+
|
190 |
+
[convolutional]
|
191 |
+
batch_normalize=1
|
192 |
+
filters=1024
|
193 |
+
size=3
|
194 |
+
stride=1
|
195 |
+
pad=1
|
196 |
+
activation=leaky
|
197 |
+
|
198 |
+
[convolutional]
|
199 |
+
filters=1000
|
200 |
+
size=1
|
201 |
+
stride=1
|
202 |
+
pad=1
|
203 |
+
activation=leaky
|
204 |
+
|
205 |
+
[avgpool]
|
206 |
+
|
207 |
+
[softmax]
|
208 |
+
groups=1
|
209 |
+
|
model/cfg/extraction.conv.cfg
ADDED
@@ -0,0 +1,179 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=1
|
3 |
+
subdivisions=1
|
4 |
+
height=256
|
5 |
+
width=256
|
6 |
+
channels=3
|
7 |
+
momentum=0.9
|
8 |
+
decay=0.0005
|
9 |
+
|
10 |
+
learning_rate=0.5
|
11 |
+
policy=poly
|
12 |
+
power=6
|
13 |
+
max_batches=500000
|
14 |
+
|
15 |
+
[convolutional]
|
16 |
+
filters=64
|
17 |
+
size=7
|
18 |
+
stride=2
|
19 |
+
pad=1
|
20 |
+
activation=leaky
|
21 |
+
|
22 |
+
[maxpool]
|
23 |
+
size=2
|
24 |
+
stride=2
|
25 |
+
|
26 |
+
[convolutional]
|
27 |
+
filters=192
|
28 |
+
size=3
|
29 |
+
stride=1
|
30 |
+
pad=1
|
31 |
+
activation=leaky
|
32 |
+
|
33 |
+
[maxpool]
|
34 |
+
size=2
|
35 |
+
stride=2
|
36 |
+
|
37 |
+
[convolutional]
|
38 |
+
filters=128
|
39 |
+
size=1
|
40 |
+
stride=1
|
41 |
+
pad=1
|
42 |
+
activation=leaky
|
43 |
+
|
44 |
+
[convolutional]
|
45 |
+
filters=256
|
46 |
+
size=3
|
47 |
+
stride=1
|
48 |
+
pad=1
|
49 |
+
activation=leaky
|
50 |
+
|
51 |
+
[convolutional]
|
52 |
+
filters=256
|
53 |
+
size=1
|
54 |
+
stride=1
|
55 |
+
pad=1
|
56 |
+
activation=leaky
|
57 |
+
|
58 |
+
[convolutional]
|
59 |
+
filters=512
|
60 |
+
size=3
|
61 |
+
stride=1
|
62 |
+
pad=1
|
63 |
+
activation=leaky
|
64 |
+
|
65 |
+
[maxpool]
|
66 |
+
size=2
|
67 |
+
stride=2
|
68 |
+
|
69 |
+
[convolutional]
|
70 |
+
filters=256
|
71 |
+
size=1
|
72 |
+
stride=1
|
73 |
+
pad=1
|
74 |
+
activation=leaky
|
75 |
+
|
76 |
+
[convolutional]
|
77 |
+
filters=512
|
78 |
+
size=3
|
79 |
+
stride=1
|
80 |
+
pad=1
|
81 |
+
activation=leaky
|
82 |
+
|
83 |
+
[convolutional]
|
84 |
+
filters=256
|
85 |
+
size=1
|
86 |
+
stride=1
|
87 |
+
pad=1
|
88 |
+
activation=leaky
|
89 |
+
|
90 |
+
[convolutional]
|
91 |
+
filters=512
|
92 |
+
size=3
|
93 |
+
stride=1
|
94 |
+
pad=1
|
95 |
+
activation=leaky
|
96 |
+
|
97 |
+
[convolutional]
|
98 |
+
filters=256
|
99 |
+
size=1
|
100 |
+
stride=1
|
101 |
+
pad=1
|
102 |
+
activation=leaky
|
103 |
+
|
104 |
+
[convolutional]
|
105 |
+
filters=512
|
106 |
+
size=3
|
107 |
+
stride=1
|
108 |
+
pad=1
|
109 |
+
activation=leaky
|
110 |
+
|
111 |
+
[convolutional]
|
112 |
+
filters=256
|
113 |
+
size=1
|
114 |
+
stride=1
|
115 |
+
pad=1
|
116 |
+
activation=leaky
|
117 |
+
|
118 |
+
[convolutional]
|
119 |
+
filters=512
|
120 |
+
size=3
|
121 |
+
stride=1
|
122 |
+
pad=1
|
123 |
+
activation=leaky
|
124 |
+
|
125 |
+
[convolutional]
|
126 |
+
filters=512
|
127 |
+
size=1
|
128 |
+
stride=1
|
129 |
+
pad=1
|
130 |
+
activation=leaky
|
131 |
+
|
132 |
+
[convolutional]
|
133 |
+
filters=1024
|
134 |
+
size=3
|
135 |
+
stride=1
|
136 |
+
pad=1
|
137 |
+
activation=leaky
|
138 |
+
|
139 |
+
[maxpool]
|
140 |
+
size=2
|
141 |
+
stride=2
|
142 |
+
|
143 |
+
[convolutional]
|
144 |
+
filters=512
|
145 |
+
size=1
|
146 |
+
stride=1
|
147 |
+
pad=1
|
148 |
+
activation=leaky
|
149 |
+
|
150 |
+
[convolutional]
|
151 |
+
filters=1024
|
152 |
+
size=3
|
153 |
+
stride=1
|
154 |
+
pad=1
|
155 |
+
activation=leaky
|
156 |
+
|
157 |
+
[convolutional]
|
158 |
+
filters=512
|
159 |
+
size=1
|
160 |
+
stride=1
|
161 |
+
pad=1
|
162 |
+
activation=leaky
|
163 |
+
|
164 |
+
[convolutional]
|
165 |
+
filters=1024
|
166 |
+
size=3
|
167 |
+
stride=1
|
168 |
+
pad=1
|
169 |
+
activation=leaky
|
170 |
+
|
171 |
+
[avgpool]
|
172 |
+
|
173 |
+
[connected]
|
174 |
+
output=1000
|
175 |
+
activation=leaky
|
176 |
+
|
177 |
+
[softmax]
|
178 |
+
groups=1
|
179 |
+
|
model/cfg/extraction22k.cfg
ADDED
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=128
|
3 |
+
subdivisions=1
|
4 |
+
height=224
|
5 |
+
width=224
|
6 |
+
max_crop=320
|
7 |
+
channels=3
|
8 |
+
momentum=0.9
|
9 |
+
decay=0.0005
|
10 |
+
|
11 |
+
learning_rate=0.01
|
12 |
+
max_batches = 0
|
13 |
+
policy=steps
|
14 |
+
steps=444000,590000,970000
|
15 |
+
scales=.5,.2,.1
|
16 |
+
|
17 |
+
#policy=sigmoid
|
18 |
+
#gamma=.00008
|
19 |
+
#step=100000
|
20 |
+
#max_batches=200000
|
21 |
+
|
22 |
+
[convolutional]
|
23 |
+
batch_normalize=1
|
24 |
+
filters=64
|
25 |
+
size=7
|
26 |
+
stride=2
|
27 |
+
pad=1
|
28 |
+
activation=leaky
|
29 |
+
|
30 |
+
[maxpool]
|
31 |
+
size=2
|
32 |
+
stride=2
|
33 |
+
|
34 |
+
[convolutional]
|
35 |
+
batch_normalize=1
|
36 |
+
filters=192
|
37 |
+
size=3
|
38 |
+
stride=1
|
39 |
+
pad=1
|
40 |
+
activation=leaky
|
41 |
+
|
42 |
+
[maxpool]
|
43 |
+
size=2
|
44 |
+
stride=2
|
45 |
+
|
46 |
+
[convolutional]
|
47 |
+
batch_normalize=1
|
48 |
+
filters=128
|
49 |
+
size=1
|
50 |
+
stride=1
|
51 |
+
pad=1
|
52 |
+
activation=leaky
|
53 |
+
|
54 |
+
[convolutional]
|
55 |
+
batch_normalize=1
|
56 |
+
filters=256
|
57 |
+
size=3
|
58 |
+
stride=1
|
59 |
+
pad=1
|
60 |
+
activation=leaky
|
61 |
+
|
62 |
+
[convolutional]
|
63 |
+
batch_normalize=1
|
64 |
+
filters=256
|
65 |
+
size=1
|
66 |
+
stride=1
|
67 |
+
pad=1
|
68 |
+
activation=leaky
|
69 |
+
|
70 |
+
[convolutional]
|
71 |
+
batch_normalize=1
|
72 |
+
filters=512
|
73 |
+
size=3
|
74 |
+
stride=1
|
75 |
+
pad=1
|
76 |
+
activation=leaky
|
77 |
+
|
78 |
+
[maxpool]
|
79 |
+
size=2
|
80 |
+
stride=2
|
81 |
+
|
82 |
+
[convolutional]
|
83 |
+
batch_normalize=1
|
84 |
+
filters=256
|
85 |
+
size=1
|
86 |
+
stride=1
|
87 |
+
pad=1
|
88 |
+
activation=leaky
|
89 |
+
|
90 |
+
[convolutional]
|
91 |
+
batch_normalize=1
|
92 |
+
filters=512
|
93 |
+
size=3
|
94 |
+
stride=1
|
95 |
+
pad=1
|
96 |
+
activation=leaky
|
97 |
+
|
98 |
+
[convolutional]
|
99 |
+
batch_normalize=1
|
100 |
+
filters=256
|
101 |
+
size=1
|
102 |
+
stride=1
|
103 |
+
pad=1
|
104 |
+
activation=leaky
|
105 |
+
|
106 |
+
[convolutional]
|
107 |
+
batch_normalize=1
|
108 |
+
filters=512
|
109 |
+
size=3
|
110 |
+
stride=1
|
111 |
+
pad=1
|
112 |
+
activation=leaky
|
113 |
+
|
114 |
+
[convolutional]
|
115 |
+
batch_normalize=1
|
116 |
+
filters=256
|
117 |
+
size=1
|
118 |
+
stride=1
|
119 |
+
pad=1
|
120 |
+
activation=leaky
|
121 |
+
|
122 |
+
[convolutional]
|
123 |
+
batch_normalize=1
|
124 |
+
filters=512
|
125 |
+
size=3
|
126 |
+
stride=1
|
127 |
+
pad=1
|
128 |
+
activation=leaky
|
129 |
+
|
130 |
+
[convolutional]
|
131 |
+
batch_normalize=1
|
132 |
+
filters=256
|
133 |
+
size=1
|
134 |
+
stride=1
|
135 |
+
pad=1
|
136 |
+
activation=leaky
|
137 |
+
|
138 |
+
[convolutional]
|
139 |
+
batch_normalize=1
|
140 |
+
filters=512
|
141 |
+
size=3
|
142 |
+
stride=1
|
143 |
+
pad=1
|
144 |
+
activation=leaky
|
145 |
+
|
146 |
+
[convolutional]
|
147 |
+
batch_normalize=1
|
148 |
+
filters=512
|
149 |
+
size=1
|
150 |
+
stride=1
|
151 |
+
pad=1
|
152 |
+
activation=leaky
|
153 |
+
|
154 |
+
[convolutional]
|
155 |
+
batch_normalize=1
|
156 |
+
filters=1024
|
157 |
+
size=3
|
158 |
+
stride=1
|
159 |
+
pad=1
|
160 |
+
activation=leaky
|
161 |
+
|
162 |
+
[maxpool]
|
163 |
+
size=2
|
164 |
+
stride=2
|
165 |
+
|
166 |
+
[convolutional]
|
167 |
+
batch_normalize=1
|
168 |
+
filters=1024
|
169 |
+
size=1
|
170 |
+
stride=1
|
171 |
+
pad=1
|
172 |
+
activation=leaky
|
173 |
+
|
174 |
+
[convolutional]
|
175 |
+
batch_normalize=1
|
176 |
+
filters=2048
|
177 |
+
size=3
|
178 |
+
stride=1
|
179 |
+
pad=1
|
180 |
+
activation=leaky
|
181 |
+
|
182 |
+
[convolutional]
|
183 |
+
batch_normalize=1
|
184 |
+
filters=1024
|
185 |
+
size=1
|
186 |
+
stride=1
|
187 |
+
pad=1
|
188 |
+
activation=leaky
|
189 |
+
|
190 |
+
[convolutional]
|
191 |
+
batch_normalize=1
|
192 |
+
filters=2048
|
193 |
+
size=3
|
194 |
+
stride=1
|
195 |
+
pad=1
|
196 |
+
activation=leaky
|
197 |
+
|
198 |
+
[avgpool]
|
199 |
+
|
200 |
+
[connected]
|
201 |
+
output=21842
|
202 |
+
activation=leaky
|
203 |
+
|
204 |
+
[softmax]
|
205 |
+
groups=1
|
206 |
+
|
model/cfg/go.cfg
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=512
|
3 |
+
subdivisions=1
|
4 |
+
height=19
|
5 |
+
width=19
|
6 |
+
channels=1
|
7 |
+
momentum=0.9
|
8 |
+
decay=0.0005
|
9 |
+
|
10 |
+
burn_in=1000
|
11 |
+
learning_rate=0.1
|
12 |
+
policy=poly
|
13 |
+
power=4
|
14 |
+
max_batches=10000000
|
15 |
+
|
16 |
+
[convolutional]
|
17 |
+
filters=256
|
18 |
+
size=3
|
19 |
+
stride=1
|
20 |
+
pad=1
|
21 |
+
activation=relu
|
22 |
+
batch_normalize=1
|
23 |
+
|
24 |
+
[convolutional]
|
25 |
+
filters=256
|
26 |
+
size=3
|
27 |
+
stride=1
|
28 |
+
pad=1
|
29 |
+
activation=relu
|
30 |
+
batch_normalize=1
|
31 |
+
|
32 |
+
[convolutional]
|
33 |
+
filters=256
|
34 |
+
size=3
|
35 |
+
stride=1
|
36 |
+
pad=1
|
37 |
+
activation=relu
|
38 |
+
batch_normalize=1
|
39 |
+
|
40 |
+
[convolutional]
|
41 |
+
filters=256
|
42 |
+
size=3
|
43 |
+
stride=1
|
44 |
+
pad=1
|
45 |
+
activation=relu
|
46 |
+
batch_normalize=1
|
47 |
+
|
48 |
+
[convolutional]
|
49 |
+
filters=256
|
50 |
+
size=3
|
51 |
+
stride=1
|
52 |
+
pad=1
|
53 |
+
activation=relu
|
54 |
+
batch_normalize=1
|
55 |
+
|
56 |
+
[convolutional]
|
57 |
+
filters=256
|
58 |
+
size=3
|
59 |
+
stride=1
|
60 |
+
pad=1
|
61 |
+
activation=relu
|
62 |
+
batch_normalize=1
|
63 |
+
|
64 |
+
[convolutional]
|
65 |
+
filters=256
|
66 |
+
size=3
|
67 |
+
stride=1
|
68 |
+
pad=1
|
69 |
+
activation=relu
|
70 |
+
batch_normalize=1
|
71 |
+
|
72 |
+
[convolutional]
|
73 |
+
filters=256
|
74 |
+
size=3
|
75 |
+
stride=1
|
76 |
+
pad=1
|
77 |
+
activation=relu
|
78 |
+
batch_normalize=1
|
79 |
+
|
80 |
+
[convolutional]
|
81 |
+
filters=256
|
82 |
+
size=3
|
83 |
+
stride=1
|
84 |
+
pad=1
|
85 |
+
activation=relu
|
86 |
+
batch_normalize=1
|
87 |
+
|
88 |
+
[convolutional]
|
89 |
+
filters=256
|
90 |
+
size=3
|
91 |
+
stride=1
|
92 |
+
pad=1
|
93 |
+
activation=relu
|
94 |
+
batch_normalize=1
|
95 |
+
|
96 |
+
[convolutional]
|
97 |
+
filters=256
|
98 |
+
size=3
|
99 |
+
stride=1
|
100 |
+
pad=1
|
101 |
+
activation=relu
|
102 |
+
batch_normalize=1
|
103 |
+
|
104 |
+
[convolutional]
|
105 |
+
filters=256
|
106 |
+
size=3
|
107 |
+
stride=1
|
108 |
+
pad=1
|
109 |
+
activation=relu
|
110 |
+
batch_normalize=1
|
111 |
+
|
112 |
+
[convolutional]
|
113 |
+
filters=256
|
114 |
+
size=3
|
115 |
+
stride=1
|
116 |
+
pad=1
|
117 |
+
activation=relu
|
118 |
+
batch_normalize=1
|
119 |
+
|
120 |
+
[convolutional]
|
121 |
+
filters=1
|
122 |
+
size=1
|
123 |
+
stride=1
|
124 |
+
pad=1
|
125 |
+
activation=linear
|
126 |
+
|
127 |
+
[reorg]
|
128 |
+
extra=1
|
129 |
+
stride=1
|
130 |
+
|
131 |
+
[softmax]
|
132 |
+
|
model/cfg/go.test.cfg
ADDED
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=1
|
3 |
+
subdivisions=1
|
4 |
+
height=19
|
5 |
+
width=19
|
6 |
+
channels=1
|
7 |
+
momentum=0.9
|
8 |
+
decay=0.0005
|
9 |
+
|
10 |
+
learning_rate=0.01
|
11 |
+
policy=poly
|
12 |
+
power=4
|
13 |
+
max_batches=100000
|
14 |
+
|
15 |
+
[convolutional]
|
16 |
+
filters=256
|
17 |
+
size=3
|
18 |
+
stride=1
|
19 |
+
pad=1
|
20 |
+
activation=relu
|
21 |
+
batch_normalize=1
|
22 |
+
|
23 |
+
[convolutional]
|
24 |
+
filters=256
|
25 |
+
size=3
|
26 |
+
stride=1
|
27 |
+
pad=1
|
28 |
+
activation=relu
|
29 |
+
batch_normalize=1
|
30 |
+
|
31 |
+
[convolutional]
|
32 |
+
filters=256
|
33 |
+
size=3
|
34 |
+
stride=1
|
35 |
+
pad=1
|
36 |
+
activation=relu
|
37 |
+
batch_normalize=1
|
38 |
+
|
39 |
+
[convolutional]
|
40 |
+
filters=256
|
41 |
+
size=3
|
42 |
+
stride=1
|
43 |
+
pad=1
|
44 |
+
activation=relu
|
45 |
+
batch_normalize=1
|
46 |
+
|
47 |
+
[convolutional]
|
48 |
+
filters=256
|
49 |
+
size=3
|
50 |
+
stride=1
|
51 |
+
pad=1
|
52 |
+
activation=relu
|
53 |
+
batch_normalize=1
|
54 |
+
|
55 |
+
[convolutional]
|
56 |
+
filters=256
|
57 |
+
size=3
|
58 |
+
stride=1
|
59 |
+
pad=1
|
60 |
+
activation=relu
|
61 |
+
batch_normalize=1
|
62 |
+
|
63 |
+
[convolutional]
|
64 |
+
filters=256
|
65 |
+
size=3
|
66 |
+
stride=1
|
67 |
+
pad=1
|
68 |
+
activation=relu
|
69 |
+
batch_normalize=1
|
70 |
+
|
71 |
+
[convolutional]
|
72 |
+
filters=256
|
73 |
+
size=3
|
74 |
+
stride=1
|
75 |
+
pad=1
|
76 |
+
activation=relu
|
77 |
+
batch_normalize=1
|
78 |
+
|
79 |
+
[convolutional]
|
80 |
+
filters=256
|
81 |
+
size=3
|
82 |
+
stride=1
|
83 |
+
pad=1
|
84 |
+
activation=relu
|
85 |
+
batch_normalize=1
|
86 |
+
|
87 |
+
[convolutional]
|
88 |
+
filters=256
|
89 |
+
size=3
|
90 |
+
stride=1
|
91 |
+
pad=1
|
92 |
+
activation=relu
|
93 |
+
batch_normalize=1
|
94 |
+
|
95 |
+
[convolutional]
|
96 |
+
filters=256
|
97 |
+
size=3
|
98 |
+
stride=1
|
99 |
+
pad=1
|
100 |
+
activation=relu
|
101 |
+
batch_normalize=1
|
102 |
+
|
103 |
+
[convolutional]
|
104 |
+
filters=256
|
105 |
+
size=3
|
106 |
+
stride=1
|
107 |
+
pad=1
|
108 |
+
activation=relu
|
109 |
+
batch_normalize=1
|
110 |
+
|
111 |
+
[convolutional]
|
112 |
+
filters=256
|
113 |
+
size=3
|
114 |
+
stride=1
|
115 |
+
pad=1
|
116 |
+
activation=relu
|
117 |
+
batch_normalize=1
|
118 |
+
|
119 |
+
[convolutional]
|
120 |
+
filters=1
|
121 |
+
size=1
|
122 |
+
stride=1
|
123 |
+
pad=1
|
124 |
+
activation=linear
|
125 |
+
|
126 |
+
[reorg]
|
127 |
+
extra=1
|
128 |
+
stride=1
|
129 |
+
|
130 |
+
[softmax]
|
131 |
+
|
132 |
+
|
model/cfg/gru.cfg
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
inputs=256
|
3 |
+
momentum=0.9
|
4 |
+
decay=0.0
|
5 |
+
subdivisions=1
|
6 |
+
batch = 1
|
7 |
+
time_steps=1
|
8 |
+
learning_rate=.002
|
9 |
+
adam=1
|
10 |
+
|
11 |
+
policy=constant
|
12 |
+
power=4
|
13 |
+
max_batches=1000000
|
14 |
+
|
15 |
+
[gru]
|
16 |
+
output = 256
|
17 |
+
|
18 |
+
[gru]
|
19 |
+
output = 256
|
20 |
+
|
21 |
+
[gru]
|
22 |
+
output = 256
|
23 |
+
|
24 |
+
[connected]
|
25 |
+
output=256
|
26 |
+
activation=linear
|
27 |
+
|
28 |
+
[softmax]
|
29 |
+
|
model/cfg/imagenet1k.data
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
classes=1000
|
2 |
+
train = /data/imagenet/imagenet1k.train.list
|
3 |
+
valid = /data/imagenet/imagenet1k.valid.list
|
4 |
+
backup = /home/pjreddie/backup/
|
5 |
+
labels = data/imagenet.labels.list
|
6 |
+
names = data/imagenet.shortnames.list
|
7 |
+
top=5
|
8 |
+
|
model/cfg/imagenet22k.dataset
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
classes=21842
|
2 |
+
train = /data/imagenet/imagenet22k.train.list
|
3 |
+
valid = /data/imagenet/imagenet22k.valid.list
|
4 |
+
#valid = /data/imagenet/imagenet1k.valid.list
|
5 |
+
backup = /home/pjreddie/backup/
|
6 |
+
labels = data/imagenet.labels.list
|
7 |
+
names = data/imagenet.shortnames.list
|
8 |
+
top = 5
|
9 |
+
|
model/cfg/imagenet9k.hierarchy.dataset
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
classes=9418
|
2 |
+
train = data/9k.train.list
|
3 |
+
valid = /data/imagenet/imagenet1k.valid.list
|
4 |
+
leaves = data/imagenet1k.labels
|
5 |
+
backup = /home/pjreddie/backup/
|
6 |
+
labels = data/9k.labels
|
7 |
+
names = data/9k.names
|
8 |
+
top=5
|
9 |
+
|
model/cfg/jnet-conv.cfg
ADDED
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=1
|
3 |
+
subdivisions=1
|
4 |
+
height=10
|
5 |
+
width=10
|
6 |
+
channels=3
|
7 |
+
learning_rate=0.01
|
8 |
+
momentum=0.9
|
9 |
+
decay=0.0005
|
10 |
+
|
11 |
+
[convolutional]
|
12 |
+
filters=32
|
13 |
+
size=3
|
14 |
+
stride=1
|
15 |
+
pad=1
|
16 |
+
activation=leaky
|
17 |
+
|
18 |
+
[convolutional]
|
19 |
+
filters=32
|
20 |
+
size=3
|
21 |
+
stride=1
|
22 |
+
pad=1
|
23 |
+
activation=leaky
|
24 |
+
|
25 |
+
[maxpool]
|
26 |
+
stride=2
|
27 |
+
size=2
|
28 |
+
|
29 |
+
[convolutional]
|
30 |
+
filters=64
|
31 |
+
size=3
|
32 |
+
stride=1
|
33 |
+
pad=1
|
34 |
+
activation=leaky
|
35 |
+
|
36 |
+
[convolutional]
|
37 |
+
filters=64
|
38 |
+
size=3
|
39 |
+
stride=1
|
40 |
+
pad=1
|
41 |
+
activation=leaky
|
42 |
+
|
43 |
+
[maxpool]
|
44 |
+
stride=2
|
45 |
+
size=2
|
46 |
+
|
47 |
+
[convolutional]
|
48 |
+
filters=128
|
49 |
+
size=3
|
50 |
+
stride=1
|
51 |
+
pad=1
|
52 |
+
activation=leaky
|
53 |
+
|
54 |
+
[convolutional]
|
55 |
+
filters=128
|
56 |
+
size=3
|
57 |
+
stride=1
|
58 |
+
pad=1
|
59 |
+
activation=leaky
|
60 |
+
|
61 |
+
[maxpool]
|
62 |
+
stride=2
|
63 |
+
size=2
|
64 |
+
|
65 |
+
[convolutional]
|
66 |
+
filters=256
|
67 |
+
size=3
|
68 |
+
stride=1
|
69 |
+
pad=1
|
70 |
+
activation=leaky
|
71 |
+
|
72 |
+
[convolutional]
|
73 |
+
filters=256
|
74 |
+
size=3
|
75 |
+
stride=1
|
76 |
+
pad=1
|
77 |
+
activation=leaky
|
78 |
+
|
79 |
+
[maxpool]
|
80 |
+
stride=2
|
81 |
+
size=2
|
82 |
+
|
83 |
+
[convolutional]
|
84 |
+
filters=512
|
85 |
+
size=3
|
86 |
+
stride=1
|
87 |
+
pad=1
|
88 |
+
activation=leaky
|
89 |
+
|
90 |
+
[convolutional]
|
91 |
+
filters=512
|
92 |
+
size=3
|
93 |
+
stride=1
|
94 |
+
pad=1
|
95 |
+
activation=leaky
|
96 |
+
|
97 |
+
[maxpool]
|
98 |
+
stride=2
|
99 |
+
size=2
|
100 |
+
|
101 |
+
[convolutional]
|
102 |
+
filters=1024
|
103 |
+
size=3
|
104 |
+
stride=1
|
105 |
+
pad=1
|
106 |
+
activation=leaky
|
107 |
+
|
108 |
+
[convolutional]
|
109 |
+
filters=1024
|
110 |
+
size=3
|
111 |
+
stride=1
|
112 |
+
pad=1
|
113 |
+
activation=leaky
|
114 |
+
|
115 |
+
[maxpool]
|
116 |
+
size=2
|
117 |
+
stride=2
|
118 |
+
|
model/cfg/openimages.data
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
classes= 601
|
2 |
+
train = /home/pjreddie/data/openimsv4/openimages.train.list
|
3 |
+
#valid = coco_testdev
|
4 |
+
valid = data/coco_val_5k.list
|
5 |
+
names = data/openimages.names
|
6 |
+
backup = /home/pjreddie/backup/
|
7 |
+
eval=coco
|
8 |
+
|
model/cfg/resnet101.cfg
ADDED
@@ -0,0 +1,990 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=2
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
channels=3
|
13 |
+
min_crop=128
|
14 |
+
max_crop=448
|
15 |
+
|
16 |
+
burn_in=1000
|
17 |
+
learning_rate=0.1
|
18 |
+
policy=poly
|
19 |
+
power=4
|
20 |
+
max_batches=800000
|
21 |
+
momentum=0.9
|
22 |
+
decay=0.0005
|
23 |
+
|
24 |
+
angle=7
|
25 |
+
hue=.1
|
26 |
+
saturation=.75
|
27 |
+
exposure=.75
|
28 |
+
aspect=.75
|
29 |
+
|
30 |
+
|
31 |
+
|
32 |
+
[convolutional]
|
33 |
+
batch_normalize=1
|
34 |
+
filters=64
|
35 |
+
size=7
|
36 |
+
stride=2
|
37 |
+
pad=1
|
38 |
+
activation=leaky
|
39 |
+
|
40 |
+
[maxpool]
|
41 |
+
size=2
|
42 |
+
stride=2
|
43 |
+
|
44 |
+
[convolutional]
|
45 |
+
batch_normalize=1
|
46 |
+
filters=64
|
47 |
+
size=1
|
48 |
+
stride=1
|
49 |
+
pad=1
|
50 |
+
activation=leaky
|
51 |
+
|
52 |
+
[convolutional]
|
53 |
+
batch_normalize=1
|
54 |
+
filters=64
|
55 |
+
size=3
|
56 |
+
stride=1
|
57 |
+
pad=1
|
58 |
+
activation=leaky
|
59 |
+
|
60 |
+
[convolutional]
|
61 |
+
batch_normalize=1
|
62 |
+
filters=256
|
63 |
+
size=1
|
64 |
+
stride=1
|
65 |
+
pad=1
|
66 |
+
activation=linear
|
67 |
+
|
68 |
+
[shortcut]
|
69 |
+
from=-4
|
70 |
+
activation=leaky
|
71 |
+
|
72 |
+
[convolutional]
|
73 |
+
batch_normalize=1
|
74 |
+
filters=64
|
75 |
+
size=1
|
76 |
+
stride=1
|
77 |
+
pad=1
|
78 |
+
activation=leaky
|
79 |
+
|
80 |
+
[convolutional]
|
81 |
+
batch_normalize=1
|
82 |
+
filters=64
|
83 |
+
size=3
|
84 |
+
stride=1
|
85 |
+
pad=1
|
86 |
+
activation=leaky
|
87 |
+
|
88 |
+
[convolutional]
|
89 |
+
batch_normalize=1
|
90 |
+
filters=256
|
91 |
+
size=1
|
92 |
+
stride=1
|
93 |
+
pad=1
|
94 |
+
activation=linear
|
95 |
+
|
96 |
+
[shortcut]
|
97 |
+
from=-4
|
98 |
+
activation=leaky
|
99 |
+
|
100 |
+
[convolutional]
|
101 |
+
batch_normalize=1
|
102 |
+
filters=64
|
103 |
+
size=1
|
104 |
+
stride=1
|
105 |
+
pad=1
|
106 |
+
activation=leaky
|
107 |
+
|
108 |
+
[convolutional]
|
109 |
+
batch_normalize=1
|
110 |
+
filters=64
|
111 |
+
size=3
|
112 |
+
stride=1
|
113 |
+
pad=1
|
114 |
+
activation=leaky
|
115 |
+
|
116 |
+
[convolutional]
|
117 |
+
batch_normalize=1
|
118 |
+
filters=256
|
119 |
+
size=1
|
120 |
+
stride=1
|
121 |
+
pad=1
|
122 |
+
activation=linear
|
123 |
+
|
124 |
+
[shortcut]
|
125 |
+
from=-4
|
126 |
+
activation=leaky
|
127 |
+
|
128 |
+
[convolutional]
|
129 |
+
batch_normalize=1
|
130 |
+
filters=128
|
131 |
+
size=1
|
132 |
+
stride=1
|
133 |
+
pad=1
|
134 |
+
activation=leaky
|
135 |
+
|
136 |
+
[convolutional]
|
137 |
+
batch_normalize=1
|
138 |
+
filters=128
|
139 |
+
size=3
|
140 |
+
stride=2
|
141 |
+
pad=1
|
142 |
+
activation=leaky
|
143 |
+
|
144 |
+
[convolutional]
|
145 |
+
batch_normalize=1
|
146 |
+
filters=512
|
147 |
+
size=1
|
148 |
+
stride=1
|
149 |
+
pad=1
|
150 |
+
activation=linear
|
151 |
+
|
152 |
+
[shortcut]
|
153 |
+
from=-4
|
154 |
+
activation=leaky
|
155 |
+
|
156 |
+
[convolutional]
|
157 |
+
batch_normalize=1
|
158 |
+
filters=128
|
159 |
+
size=1
|
160 |
+
stride=1
|
161 |
+
pad=1
|
162 |
+
activation=leaky
|
163 |
+
|
164 |
+
[convolutional]
|
165 |
+
batch_normalize=1
|
166 |
+
filters=128
|
167 |
+
size=3
|
168 |
+
stride=1
|
169 |
+
pad=1
|
170 |
+
activation=leaky
|
171 |
+
|
172 |
+
[convolutional]
|
173 |
+
batch_normalize=1
|
174 |
+
filters=512
|
175 |
+
size=1
|
176 |
+
stride=1
|
177 |
+
pad=1
|
178 |
+
activation=linear
|
179 |
+
|
180 |
+
[shortcut]
|
181 |
+
from=-4
|
182 |
+
activation=leaky
|
183 |
+
|
184 |
+
[convolutional]
|
185 |
+
batch_normalize=1
|
186 |
+
filters=128
|
187 |
+
size=1
|
188 |
+
stride=1
|
189 |
+
pad=1
|
190 |
+
activation=leaky
|
191 |
+
|
192 |
+
[convolutional]
|
193 |
+
batch_normalize=1
|
194 |
+
filters=128
|
195 |
+
size=3
|
196 |
+
stride=1
|
197 |
+
pad=1
|
198 |
+
activation=leaky
|
199 |
+
|
200 |
+
[convolutional]
|
201 |
+
batch_normalize=1
|
202 |
+
filters=512
|
203 |
+
size=1
|
204 |
+
stride=1
|
205 |
+
pad=1
|
206 |
+
activation=linear
|
207 |
+
|
208 |
+
[shortcut]
|
209 |
+
from=-4
|
210 |
+
activation=leaky
|
211 |
+
|
212 |
+
[convolutional]
|
213 |
+
batch_normalize=1
|
214 |
+
filters=128
|
215 |
+
size=1
|
216 |
+
stride=1
|
217 |
+
pad=1
|
218 |
+
activation=leaky
|
219 |
+
|
220 |
+
[convolutional]
|
221 |
+
batch_normalize=1
|
222 |
+
filters=128
|
223 |
+
size=3
|
224 |
+
stride=1
|
225 |
+
pad=1
|
226 |
+
activation=leaky
|
227 |
+
|
228 |
+
[convolutional]
|
229 |
+
batch_normalize=1
|
230 |
+
filters=512
|
231 |
+
size=1
|
232 |
+
stride=1
|
233 |
+
pad=1
|
234 |
+
activation=linear
|
235 |
+
|
236 |
+
[shortcut]
|
237 |
+
from=-4
|
238 |
+
activation=leaky
|
239 |
+
|
240 |
+
|
241 |
+
# Conv 4
|
242 |
+
[convolutional]
|
243 |
+
batch_normalize=1
|
244 |
+
filters=256
|
245 |
+
size=1
|
246 |
+
stride=1
|
247 |
+
pad=1
|
248 |
+
activation=leaky
|
249 |
+
|
250 |
+
[convolutional]
|
251 |
+
batch_normalize=1
|
252 |
+
filters=256
|
253 |
+
size=3
|
254 |
+
stride=2
|
255 |
+
pad=1
|
256 |
+
activation=leaky
|
257 |
+
|
258 |
+
[convolutional]
|
259 |
+
batch_normalize=1
|
260 |
+
filters=1024
|
261 |
+
size=1
|
262 |
+
stride=1
|
263 |
+
pad=1
|
264 |
+
activation=linear
|
265 |
+
|
266 |
+
[shortcut]
|
267 |
+
from=-4
|
268 |
+
activation=leaky
|
269 |
+
|
270 |
+
[convolutional]
|
271 |
+
batch_normalize=1
|
272 |
+
filters=256
|
273 |
+
size=1
|
274 |
+
stride=1
|
275 |
+
pad=1
|
276 |
+
activation=leaky
|
277 |
+
|
278 |
+
[convolutional]
|
279 |
+
batch_normalize=1
|
280 |
+
filters=256
|
281 |
+
size=3
|
282 |
+
stride=1
|
283 |
+
pad=1
|
284 |
+
activation=leaky
|
285 |
+
|
286 |
+
[convolutional]
|
287 |
+
batch_normalize=1
|
288 |
+
filters=1024
|
289 |
+
size=1
|
290 |
+
stride=1
|
291 |
+
pad=1
|
292 |
+
activation=linear
|
293 |
+
|
294 |
+
[shortcut]
|
295 |
+
from=-4
|
296 |
+
activation=leaky
|
297 |
+
|
298 |
+
[convolutional]
|
299 |
+
batch_normalize=1
|
300 |
+
filters=256
|
301 |
+
size=1
|
302 |
+
stride=1
|
303 |
+
pad=1
|
304 |
+
activation=leaky
|
305 |
+
|
306 |
+
[convolutional]
|
307 |
+
batch_normalize=1
|
308 |
+
filters=256
|
309 |
+
size=3
|
310 |
+
stride=1
|
311 |
+
pad=1
|
312 |
+
activation=leaky
|
313 |
+
|
314 |
+
[convolutional]
|
315 |
+
batch_normalize=1
|
316 |
+
filters=1024
|
317 |
+
size=1
|
318 |
+
stride=1
|
319 |
+
pad=1
|
320 |
+
activation=linear
|
321 |
+
|
322 |
+
[shortcut]
|
323 |
+
from=-4
|
324 |
+
activation=leaky
|
325 |
+
|
326 |
+
[convolutional]
|
327 |
+
batch_normalize=1
|
328 |
+
filters=256
|
329 |
+
size=1
|
330 |
+
stride=1
|
331 |
+
pad=1
|
332 |
+
activation=leaky
|
333 |
+
|
334 |
+
[convolutional]
|
335 |
+
batch_normalize=1
|
336 |
+
filters=256
|
337 |
+
size=3
|
338 |
+
stride=1
|
339 |
+
pad=1
|
340 |
+
activation=leaky
|
341 |
+
|
342 |
+
[convolutional]
|
343 |
+
batch_normalize=1
|
344 |
+
filters=1024
|
345 |
+
size=1
|
346 |
+
stride=1
|
347 |
+
pad=1
|
348 |
+
activation=linear
|
349 |
+
|
350 |
+
[shortcut]
|
351 |
+
from=-4
|
352 |
+
activation=leaky
|
353 |
+
|
354 |
+
[convolutional]
|
355 |
+
batch_normalize=1
|
356 |
+
filters=256
|
357 |
+
size=1
|
358 |
+
stride=1
|
359 |
+
pad=1
|
360 |
+
activation=leaky
|
361 |
+
|
362 |
+
[convolutional]
|
363 |
+
batch_normalize=1
|
364 |
+
filters=256
|
365 |
+
size=3
|
366 |
+
stride=1
|
367 |
+
pad=1
|
368 |
+
activation=leaky
|
369 |
+
|
370 |
+
[convolutional]
|
371 |
+
batch_normalize=1
|
372 |
+
filters=1024
|
373 |
+
size=1
|
374 |
+
stride=1
|
375 |
+
pad=1
|
376 |
+
activation=linear
|
377 |
+
|
378 |
+
[shortcut]
|
379 |
+
from=-4
|
380 |
+
activation=leaky
|
381 |
+
|
382 |
+
[convolutional]
|
383 |
+
batch_normalize=1
|
384 |
+
filters=256
|
385 |
+
size=1
|
386 |
+
stride=1
|
387 |
+
pad=1
|
388 |
+
activation=leaky
|
389 |
+
|
390 |
+
[convolutional]
|
391 |
+
batch_normalize=1
|
392 |
+
filters=256
|
393 |
+
size=3
|
394 |
+
stride=1
|
395 |
+
pad=1
|
396 |
+
activation=leaky
|
397 |
+
|
398 |
+
[convolutional]
|
399 |
+
batch_normalize=1
|
400 |
+
filters=1024
|
401 |
+
size=1
|
402 |
+
stride=1
|
403 |
+
pad=1
|
404 |
+
activation=linear
|
405 |
+
|
406 |
+
[shortcut]
|
407 |
+
from=-4
|
408 |
+
activation=leaky
|
409 |
+
|
410 |
+
[convolutional]
|
411 |
+
batch_normalize=1
|
412 |
+
filters=256
|
413 |
+
size=1
|
414 |
+
stride=1
|
415 |
+
pad=1
|
416 |
+
activation=leaky
|
417 |
+
|
418 |
+
[convolutional]
|
419 |
+
batch_normalize=1
|
420 |
+
filters=256
|
421 |
+
size=3
|
422 |
+
stride=1
|
423 |
+
pad=1
|
424 |
+
activation=leaky
|
425 |
+
|
426 |
+
[convolutional]
|
427 |
+
batch_normalize=1
|
428 |
+
filters=1024
|
429 |
+
size=1
|
430 |
+
stride=1
|
431 |
+
pad=1
|
432 |
+
activation=linear
|
433 |
+
|
434 |
+
[shortcut]
|
435 |
+
from=-4
|
436 |
+
activation=leaky
|
437 |
+
|
438 |
+
[convolutional]
|
439 |
+
batch_normalize=1
|
440 |
+
filters=256
|
441 |
+
size=1
|
442 |
+
stride=1
|
443 |
+
pad=1
|
444 |
+
activation=leaky
|
445 |
+
|
446 |
+
[convolutional]
|
447 |
+
batch_normalize=1
|
448 |
+
filters=256
|
449 |
+
size=3
|
450 |
+
stride=1
|
451 |
+
pad=1
|
452 |
+
activation=leaky
|
453 |
+
|
454 |
+
[convolutional]
|
455 |
+
batch_normalize=1
|
456 |
+
filters=1024
|
457 |
+
size=1
|
458 |
+
stride=1
|
459 |
+
pad=1
|
460 |
+
activation=linear
|
461 |
+
|
462 |
+
[shortcut]
|
463 |
+
from=-4
|
464 |
+
activation=leaky
|
465 |
+
|
466 |
+
[convolutional]
|
467 |
+
batch_normalize=1
|
468 |
+
filters=256
|
469 |
+
size=1
|
470 |
+
stride=1
|
471 |
+
pad=1
|
472 |
+
activation=leaky
|
473 |
+
|
474 |
+
[convolutional]
|
475 |
+
batch_normalize=1
|
476 |
+
filters=256
|
477 |
+
size=3
|
478 |
+
stride=1
|
479 |
+
pad=1
|
480 |
+
activation=leaky
|
481 |
+
|
482 |
+
[convolutional]
|
483 |
+
batch_normalize=1
|
484 |
+
filters=1024
|
485 |
+
size=1
|
486 |
+
stride=1
|
487 |
+
pad=1
|
488 |
+
activation=linear
|
489 |
+
|
490 |
+
[shortcut]
|
491 |
+
from=-4
|
492 |
+
activation=leaky
|
493 |
+
|
494 |
+
[convolutional]
|
495 |
+
batch_normalize=1
|
496 |
+
filters=256
|
497 |
+
size=1
|
498 |
+
stride=1
|
499 |
+
pad=1
|
500 |
+
activation=leaky
|
501 |
+
|
502 |
+
[convolutional]
|
503 |
+
batch_normalize=1
|
504 |
+
filters=256
|
505 |
+
size=3
|
506 |
+
stride=1
|
507 |
+
pad=1
|
508 |
+
activation=leaky
|
509 |
+
|
510 |
+
[convolutional]
|
511 |
+
batch_normalize=1
|
512 |
+
filters=1024
|
513 |
+
size=1
|
514 |
+
stride=1
|
515 |
+
pad=1
|
516 |
+
activation=linear
|
517 |
+
|
518 |
+
[shortcut]
|
519 |
+
from=-4
|
520 |
+
activation=leaky
|
521 |
+
|
522 |
+
[convolutional]
|
523 |
+
batch_normalize=1
|
524 |
+
filters=256
|
525 |
+
size=1
|
526 |
+
stride=1
|
527 |
+
pad=1
|
528 |
+
activation=leaky
|
529 |
+
|
530 |
+
[convolutional]
|
531 |
+
batch_normalize=1
|
532 |
+
filters=256
|
533 |
+
size=3
|
534 |
+
stride=1
|
535 |
+
pad=1
|
536 |
+
activation=leaky
|
537 |
+
|
538 |
+
[convolutional]
|
539 |
+
batch_normalize=1
|
540 |
+
filters=1024
|
541 |
+
size=1
|
542 |
+
stride=1
|
543 |
+
pad=1
|
544 |
+
activation=linear
|
545 |
+
|
546 |
+
[shortcut]
|
547 |
+
from=-4
|
548 |
+
activation=leaky
|
549 |
+
|
550 |
+
[convolutional]
|
551 |
+
batch_normalize=1
|
552 |
+
filters=256
|
553 |
+
size=1
|
554 |
+
stride=1
|
555 |
+
pad=1
|
556 |
+
activation=leaky
|
557 |
+
|
558 |
+
[convolutional]
|
559 |
+
batch_normalize=1
|
560 |
+
filters=256
|
561 |
+
size=3
|
562 |
+
stride=1
|
563 |
+
pad=1
|
564 |
+
activation=leaky
|
565 |
+
|
566 |
+
[convolutional]
|
567 |
+
batch_normalize=1
|
568 |
+
filters=1024
|
569 |
+
size=1
|
570 |
+
stride=1
|
571 |
+
pad=1
|
572 |
+
activation=linear
|
573 |
+
|
574 |
+
[shortcut]
|
575 |
+
from=-4
|
576 |
+
activation=leaky
|
577 |
+
|
578 |
+
[convolutional]
|
579 |
+
batch_normalize=1
|
580 |
+
filters=256
|
581 |
+
size=1
|
582 |
+
stride=1
|
583 |
+
pad=1
|
584 |
+
activation=leaky
|
585 |
+
|
586 |
+
[convolutional]
|
587 |
+
batch_normalize=1
|
588 |
+
filters=256
|
589 |
+
size=3
|
590 |
+
stride=1
|
591 |
+
pad=1
|
592 |
+
activation=leaky
|
593 |
+
|
594 |
+
[convolutional]
|
595 |
+
batch_normalize=1
|
596 |
+
filters=1024
|
597 |
+
size=1
|
598 |
+
stride=1
|
599 |
+
pad=1
|
600 |
+
activation=linear
|
601 |
+
|
602 |
+
[shortcut]
|
603 |
+
from=-4
|
604 |
+
activation=leaky
|
605 |
+
|
606 |
+
[convolutional]
|
607 |
+
batch_normalize=1
|
608 |
+
filters=256
|
609 |
+
size=1
|
610 |
+
stride=1
|
611 |
+
pad=1
|
612 |
+
activation=leaky
|
613 |
+
|
614 |
+
[convolutional]
|
615 |
+
batch_normalize=1
|
616 |
+
filters=256
|
617 |
+
size=3
|
618 |
+
stride=1
|
619 |
+
pad=1
|
620 |
+
activation=leaky
|
621 |
+
|
622 |
+
[convolutional]
|
623 |
+
batch_normalize=1
|
624 |
+
filters=1024
|
625 |
+
size=1
|
626 |
+
stride=1
|
627 |
+
pad=1
|
628 |
+
activation=linear
|
629 |
+
|
630 |
+
[shortcut]
|
631 |
+
from=-4
|
632 |
+
activation=leaky
|
633 |
+
|
634 |
+
[convolutional]
|
635 |
+
batch_normalize=1
|
636 |
+
filters=256
|
637 |
+
size=1
|
638 |
+
stride=1
|
639 |
+
pad=1
|
640 |
+
activation=leaky
|
641 |
+
|
642 |
+
[convolutional]
|
643 |
+
batch_normalize=1
|
644 |
+
filters=256
|
645 |
+
size=3
|
646 |
+
stride=1
|
647 |
+
pad=1
|
648 |
+
activation=leaky
|
649 |
+
|
650 |
+
[convolutional]
|
651 |
+
batch_normalize=1
|
652 |
+
filters=1024
|
653 |
+
size=1
|
654 |
+
stride=1
|
655 |
+
pad=1
|
656 |
+
activation=linear
|
657 |
+
|
658 |
+
[shortcut]
|
659 |
+
from=-4
|
660 |
+
activation=leaky
|
661 |
+
|
662 |
+
[convolutional]
|
663 |
+
batch_normalize=1
|
664 |
+
filters=256
|
665 |
+
size=1
|
666 |
+
stride=1
|
667 |
+
pad=1
|
668 |
+
activation=leaky
|
669 |
+
|
670 |
+
[convolutional]
|
671 |
+
batch_normalize=1
|
672 |
+
filters=256
|
673 |
+
size=3
|
674 |
+
stride=1
|
675 |
+
pad=1
|
676 |
+
activation=leaky
|
677 |
+
|
678 |
+
[convolutional]
|
679 |
+
batch_normalize=1
|
680 |
+
filters=1024
|
681 |
+
size=1
|
682 |
+
stride=1
|
683 |
+
pad=1
|
684 |
+
activation=linear
|
685 |
+
|
686 |
+
[shortcut]
|
687 |
+
from=-4
|
688 |
+
activation=leaky
|
689 |
+
|
690 |
+
[convolutional]
|
691 |
+
batch_normalize=1
|
692 |
+
filters=256
|
693 |
+
size=1
|
694 |
+
stride=1
|
695 |
+
pad=1
|
696 |
+
activation=leaky
|
697 |
+
|
698 |
+
[convolutional]
|
699 |
+
batch_normalize=1
|
700 |
+
filters=256
|
701 |
+
size=3
|
702 |
+
stride=1
|
703 |
+
pad=1
|
704 |
+
activation=leaky
|
705 |
+
|
706 |
+
[convolutional]
|
707 |
+
batch_normalize=1
|
708 |
+
filters=1024
|
709 |
+
size=1
|
710 |
+
stride=1
|
711 |
+
pad=1
|
712 |
+
activation=linear
|
713 |
+
|
714 |
+
[shortcut]
|
715 |
+
from=-4
|
716 |
+
activation=leaky
|
717 |
+
|
718 |
+
[convolutional]
|
719 |
+
batch_normalize=1
|
720 |
+
filters=256
|
721 |
+
size=1
|
722 |
+
stride=1
|
723 |
+
pad=1
|
724 |
+
activation=leaky
|
725 |
+
|
726 |
+
[convolutional]
|
727 |
+
batch_normalize=1
|
728 |
+
filters=256
|
729 |
+
size=3
|
730 |
+
stride=1
|
731 |
+
pad=1
|
732 |
+
activation=leaky
|
733 |
+
|
734 |
+
[convolutional]
|
735 |
+
batch_normalize=1
|
736 |
+
filters=1024
|
737 |
+
size=1
|
738 |
+
stride=1
|
739 |
+
pad=1
|
740 |
+
activation=linear
|
741 |
+
|
742 |
+
[shortcut]
|
743 |
+
from=-4
|
744 |
+
activation=leaky
|
745 |
+
|
746 |
+
[convolutional]
|
747 |
+
batch_normalize=1
|
748 |
+
filters=256
|
749 |
+
size=1
|
750 |
+
stride=1
|
751 |
+
pad=1
|
752 |
+
activation=leaky
|
753 |
+
|
754 |
+
[convolutional]
|
755 |
+
batch_normalize=1
|
756 |
+
filters=256
|
757 |
+
size=3
|
758 |
+
stride=1
|
759 |
+
pad=1
|
760 |
+
activation=leaky
|
761 |
+
|
762 |
+
[convolutional]
|
763 |
+
batch_normalize=1
|
764 |
+
filters=1024
|
765 |
+
size=1
|
766 |
+
stride=1
|
767 |
+
pad=1
|
768 |
+
activation=linear
|
769 |
+
|
770 |
+
[shortcut]
|
771 |
+
from=-4
|
772 |
+
activation=leaky
|
773 |
+
|
774 |
+
[convolutional]
|
775 |
+
batch_normalize=1
|
776 |
+
filters=256
|
777 |
+
size=1
|
778 |
+
stride=1
|
779 |
+
pad=1
|
780 |
+
activation=leaky
|
781 |
+
|
782 |
+
[convolutional]
|
783 |
+
batch_normalize=1
|
784 |
+
filters=256
|
785 |
+
size=3
|
786 |
+
stride=1
|
787 |
+
pad=1
|
788 |
+
activation=leaky
|
789 |
+
|
790 |
+
[convolutional]
|
791 |
+
batch_normalize=1
|
792 |
+
filters=1024
|
793 |
+
size=1
|
794 |
+
stride=1
|
795 |
+
pad=1
|
796 |
+
activation=linear
|
797 |
+
|
798 |
+
[shortcut]
|
799 |
+
from=-4
|
800 |
+
activation=leaky
|
801 |
+
|
802 |
+
[convolutional]
|
803 |
+
batch_normalize=1
|
804 |
+
filters=256
|
805 |
+
size=1
|
806 |
+
stride=1
|
807 |
+
pad=1
|
808 |
+
activation=leaky
|
809 |
+
|
810 |
+
[convolutional]
|
811 |
+
batch_normalize=1
|
812 |
+
filters=256
|
813 |
+
size=3
|
814 |
+
stride=1
|
815 |
+
pad=1
|
816 |
+
activation=leaky
|
817 |
+
|
818 |
+
[convolutional]
|
819 |
+
batch_normalize=1
|
820 |
+
filters=1024
|
821 |
+
size=1
|
822 |
+
stride=1
|
823 |
+
pad=1
|
824 |
+
activation=linear
|
825 |
+
|
826 |
+
[shortcut]
|
827 |
+
from=-4
|
828 |
+
activation=leaky
|
829 |
+
|
830 |
+
[convolutional]
|
831 |
+
batch_normalize=1
|
832 |
+
filters=256
|
833 |
+
size=1
|
834 |
+
stride=1
|
835 |
+
pad=1
|
836 |
+
activation=leaky
|
837 |
+
|
838 |
+
[convolutional]
|
839 |
+
batch_normalize=1
|
840 |
+
filters=256
|
841 |
+
size=3
|
842 |
+
stride=1
|
843 |
+
pad=1
|
844 |
+
activation=leaky
|
845 |
+
|
846 |
+
[convolutional]
|
847 |
+
batch_normalize=1
|
848 |
+
filters=1024
|
849 |
+
size=1
|
850 |
+
stride=1
|
851 |
+
pad=1
|
852 |
+
activation=linear
|
853 |
+
|
854 |
+
[shortcut]
|
855 |
+
from=-4
|
856 |
+
activation=leaky
|
857 |
+
|
858 |
+
[convolutional]
|
859 |
+
batch_normalize=1
|
860 |
+
filters=256
|
861 |
+
size=1
|
862 |
+
stride=1
|
863 |
+
pad=1
|
864 |
+
activation=leaky
|
865 |
+
|
866 |
+
[convolutional]
|
867 |
+
batch_normalize=1
|
868 |
+
filters=256
|
869 |
+
size=3
|
870 |
+
stride=1
|
871 |
+
pad=1
|
872 |
+
activation=leaky
|
873 |
+
|
874 |
+
[convolutional]
|
875 |
+
batch_normalize=1
|
876 |
+
filters=1024
|
877 |
+
size=1
|
878 |
+
stride=1
|
879 |
+
pad=1
|
880 |
+
activation=linear
|
881 |
+
|
882 |
+
[shortcut]
|
883 |
+
from=-4
|
884 |
+
activation=leaky
|
885 |
+
|
886 |
+
#Conv 5
|
887 |
+
[convolutional]
|
888 |
+
batch_normalize=1
|
889 |
+
filters=512
|
890 |
+
size=1
|
891 |
+
stride=1
|
892 |
+
pad=1
|
893 |
+
activation=leaky
|
894 |
+
|
895 |
+
[convolutional]
|
896 |
+
batch_normalize=1
|
897 |
+
filters=512
|
898 |
+
size=3
|
899 |
+
stride=2
|
900 |
+
pad=1
|
901 |
+
activation=leaky
|
902 |
+
|
903 |
+
[convolutional]
|
904 |
+
batch_normalize=1
|
905 |
+
filters=2048
|
906 |
+
size=1
|
907 |
+
stride=1
|
908 |
+
pad=1
|
909 |
+
activation=linear
|
910 |
+
|
911 |
+
[shortcut]
|
912 |
+
from=-4
|
913 |
+
activation=leaky
|
914 |
+
|
915 |
+
[convolutional]
|
916 |
+
batch_normalize=1
|
917 |
+
filters=512
|
918 |
+
size=1
|
919 |
+
stride=1
|
920 |
+
pad=1
|
921 |
+
activation=leaky
|
922 |
+
|
923 |
+
[convolutional]
|
924 |
+
batch_normalize=1
|
925 |
+
filters=512
|
926 |
+
size=3
|
927 |
+
stride=1
|
928 |
+
pad=1
|
929 |
+
activation=leaky
|
930 |
+
|
931 |
+
[convolutional]
|
932 |
+
batch_normalize=1
|
933 |
+
filters=2048
|
934 |
+
size=1
|
935 |
+
stride=1
|
936 |
+
pad=1
|
937 |
+
activation=linear
|
938 |
+
|
939 |
+
[shortcut]
|
940 |
+
from=-4
|
941 |
+
activation=leaky
|
942 |
+
|
943 |
+
[convolutional]
|
944 |
+
batch_normalize=1
|
945 |
+
filters=512
|
946 |
+
size=1
|
947 |
+
stride=1
|
948 |
+
pad=1
|
949 |
+
activation=leaky
|
950 |
+
|
951 |
+
[convolutional]
|
952 |
+
batch_normalize=1
|
953 |
+
filters=512
|
954 |
+
size=3
|
955 |
+
stride=1
|
956 |
+
pad=1
|
957 |
+
activation=leaky
|
958 |
+
|
959 |
+
[convolutional]
|
960 |
+
batch_normalize=1
|
961 |
+
filters=2048
|
962 |
+
size=1
|
963 |
+
stride=1
|
964 |
+
pad=1
|
965 |
+
activation=linear
|
966 |
+
|
967 |
+
[shortcut]
|
968 |
+
from=-4
|
969 |
+
activation=leaky
|
970 |
+
|
971 |
+
|
972 |
+
|
973 |
+
|
974 |
+
|
975 |
+
|
976 |
+
[convolutional]
|
977 |
+
filters=1000
|
978 |
+
size=1
|
979 |
+
stride=1
|
980 |
+
pad=1
|
981 |
+
activation=linear
|
982 |
+
|
983 |
+
[avgpool]
|
984 |
+
|
985 |
+
[softmax]
|
986 |
+
groups=1
|
987 |
+
|
988 |
+
[cost]
|
989 |
+
type=sse
|
990 |
+
|
model/cfg/resnet152.cfg
ADDED
@@ -0,0 +1,1460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=8
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
max_crop=448
|
13 |
+
channels=3
|
14 |
+
momentum=0.9
|
15 |
+
decay=0.0005
|
16 |
+
|
17 |
+
burn_in=1000
|
18 |
+
learning_rate=0.1
|
19 |
+
policy=poly
|
20 |
+
power=4
|
21 |
+
max_batches=1600000
|
22 |
+
|
23 |
+
angle=7
|
24 |
+
hue=.1
|
25 |
+
saturation=.75
|
26 |
+
exposure=.75
|
27 |
+
aspect=.75
|
28 |
+
|
29 |
+
[convolutional]
|
30 |
+
batch_normalize=1
|
31 |
+
filters=64
|
32 |
+
size=7
|
33 |
+
stride=2
|
34 |
+
pad=1
|
35 |
+
activation=leaky
|
36 |
+
|
37 |
+
[maxpool]
|
38 |
+
size=2
|
39 |
+
stride=2
|
40 |
+
|
41 |
+
[convolutional]
|
42 |
+
batch_normalize=1
|
43 |
+
filters=64
|
44 |
+
size=1
|
45 |
+
stride=1
|
46 |
+
pad=1
|
47 |
+
activation=leaky
|
48 |
+
|
49 |
+
[convolutional]
|
50 |
+
batch_normalize=1
|
51 |
+
filters=64
|
52 |
+
size=3
|
53 |
+
stride=1
|
54 |
+
pad=1
|
55 |
+
activation=leaky
|
56 |
+
|
57 |
+
[convolutional]
|
58 |
+
batch_normalize=1
|
59 |
+
filters=256
|
60 |
+
size=1
|
61 |
+
stride=1
|
62 |
+
pad=1
|
63 |
+
activation=linear
|
64 |
+
|
65 |
+
[shortcut]
|
66 |
+
from=-4
|
67 |
+
activation=leaky
|
68 |
+
|
69 |
+
[convolutional]
|
70 |
+
batch_normalize=1
|
71 |
+
filters=64
|
72 |
+
size=1
|
73 |
+
stride=1
|
74 |
+
pad=1
|
75 |
+
activation=leaky
|
76 |
+
|
77 |
+
[convolutional]
|
78 |
+
batch_normalize=1
|
79 |
+
filters=64
|
80 |
+
size=3
|
81 |
+
stride=1
|
82 |
+
pad=1
|
83 |
+
activation=leaky
|
84 |
+
|
85 |
+
[convolutional]
|
86 |
+
batch_normalize=1
|
87 |
+
filters=256
|
88 |
+
size=1
|
89 |
+
stride=1
|
90 |
+
pad=1
|
91 |
+
activation=linear
|
92 |
+
|
93 |
+
[shortcut]
|
94 |
+
from=-4
|
95 |
+
activation=leaky
|
96 |
+
|
97 |
+
[convolutional]
|
98 |
+
batch_normalize=1
|
99 |
+
filters=64
|
100 |
+
size=1
|
101 |
+
stride=1
|
102 |
+
pad=1
|
103 |
+
activation=leaky
|
104 |
+
|
105 |
+
[convolutional]
|
106 |
+
batch_normalize=1
|
107 |
+
filters=64
|
108 |
+
size=3
|
109 |
+
stride=1
|
110 |
+
pad=1
|
111 |
+
activation=leaky
|
112 |
+
|
113 |
+
[convolutional]
|
114 |
+
batch_normalize=1
|
115 |
+
filters=256
|
116 |
+
size=1
|
117 |
+
stride=1
|
118 |
+
pad=1
|
119 |
+
activation=linear
|
120 |
+
|
121 |
+
[shortcut]
|
122 |
+
from=-4
|
123 |
+
activation=leaky
|
124 |
+
|
125 |
+
[convolutional]
|
126 |
+
batch_normalize=1
|
127 |
+
filters=128
|
128 |
+
size=1
|
129 |
+
stride=1
|
130 |
+
pad=1
|
131 |
+
activation=leaky
|
132 |
+
|
133 |
+
[convolutional]
|
134 |
+
batch_normalize=1
|
135 |
+
filters=128
|
136 |
+
size=3
|
137 |
+
stride=2
|
138 |
+
pad=1
|
139 |
+
activation=leaky
|
140 |
+
|
141 |
+
[convolutional]
|
142 |
+
batch_normalize=1
|
143 |
+
filters=512
|
144 |
+
size=1
|
145 |
+
stride=1
|
146 |
+
pad=1
|
147 |
+
activation=linear
|
148 |
+
|
149 |
+
[shortcut]
|
150 |
+
from=-4
|
151 |
+
activation=leaky
|
152 |
+
|
153 |
+
[convolutional]
|
154 |
+
batch_normalize=1
|
155 |
+
filters=128
|
156 |
+
size=1
|
157 |
+
stride=1
|
158 |
+
pad=1
|
159 |
+
activation=leaky
|
160 |
+
|
161 |
+
[convolutional]
|
162 |
+
batch_normalize=1
|
163 |
+
filters=128
|
164 |
+
size=3
|
165 |
+
stride=1
|
166 |
+
pad=1
|
167 |
+
activation=leaky
|
168 |
+
|
169 |
+
[convolutional]
|
170 |
+
batch_normalize=1
|
171 |
+
filters=512
|
172 |
+
size=1
|
173 |
+
stride=1
|
174 |
+
pad=1
|
175 |
+
activation=linear
|
176 |
+
|
177 |
+
[shortcut]
|
178 |
+
from=-4
|
179 |
+
activation=leaky
|
180 |
+
|
181 |
+
[convolutional]
|
182 |
+
batch_normalize=1
|
183 |
+
filters=128
|
184 |
+
size=1
|
185 |
+
stride=1
|
186 |
+
pad=1
|
187 |
+
activation=leaky
|
188 |
+
|
189 |
+
[convolutional]
|
190 |
+
batch_normalize=1
|
191 |
+
filters=128
|
192 |
+
size=3
|
193 |
+
stride=1
|
194 |
+
pad=1
|
195 |
+
activation=leaky
|
196 |
+
|
197 |
+
[convolutional]
|
198 |
+
batch_normalize=1
|
199 |
+
filters=512
|
200 |
+
size=1
|
201 |
+
stride=1
|
202 |
+
pad=1
|
203 |
+
activation=linear
|
204 |
+
|
205 |
+
[shortcut]
|
206 |
+
from=-4
|
207 |
+
activation=leaky
|
208 |
+
|
209 |
+
[convolutional]
|
210 |
+
batch_normalize=1
|
211 |
+
filters=128
|
212 |
+
size=1
|
213 |
+
stride=1
|
214 |
+
pad=1
|
215 |
+
activation=leaky
|
216 |
+
|
217 |
+
[convolutional]
|
218 |
+
batch_normalize=1
|
219 |
+
filters=128
|
220 |
+
size=3
|
221 |
+
stride=1
|
222 |
+
pad=1
|
223 |
+
activation=leaky
|
224 |
+
|
225 |
+
[convolutional]
|
226 |
+
batch_normalize=1
|
227 |
+
filters=512
|
228 |
+
size=1
|
229 |
+
stride=1
|
230 |
+
pad=1
|
231 |
+
activation=linear
|
232 |
+
|
233 |
+
[shortcut]
|
234 |
+
from=-4
|
235 |
+
activation=leaky
|
236 |
+
|
237 |
+
[convolutional]
|
238 |
+
batch_normalize=1
|
239 |
+
filters=128
|
240 |
+
size=1
|
241 |
+
stride=1
|
242 |
+
pad=1
|
243 |
+
activation=leaky
|
244 |
+
|
245 |
+
[convolutional]
|
246 |
+
batch_normalize=1
|
247 |
+
filters=128
|
248 |
+
size=3
|
249 |
+
stride=1
|
250 |
+
pad=1
|
251 |
+
activation=leaky
|
252 |
+
|
253 |
+
[convolutional]
|
254 |
+
batch_normalize=1
|
255 |
+
filters=512
|
256 |
+
size=1
|
257 |
+
stride=1
|
258 |
+
pad=1
|
259 |
+
activation=linear
|
260 |
+
|
261 |
+
[shortcut]
|
262 |
+
from=-4
|
263 |
+
activation=leaky
|
264 |
+
|
265 |
+
[convolutional]
|
266 |
+
batch_normalize=1
|
267 |
+
filters=128
|
268 |
+
size=1
|
269 |
+
stride=1
|
270 |
+
pad=1
|
271 |
+
activation=leaky
|
272 |
+
|
273 |
+
[convolutional]
|
274 |
+
batch_normalize=1
|
275 |
+
filters=128
|
276 |
+
size=3
|
277 |
+
stride=1
|
278 |
+
pad=1
|
279 |
+
activation=leaky
|
280 |
+
|
281 |
+
[convolutional]
|
282 |
+
batch_normalize=1
|
283 |
+
filters=512
|
284 |
+
size=1
|
285 |
+
stride=1
|
286 |
+
pad=1
|
287 |
+
activation=linear
|
288 |
+
|
289 |
+
[shortcut]
|
290 |
+
from=-4
|
291 |
+
activation=leaky
|
292 |
+
|
293 |
+
[convolutional]
|
294 |
+
batch_normalize=1
|
295 |
+
filters=128
|
296 |
+
size=1
|
297 |
+
stride=1
|
298 |
+
pad=1
|
299 |
+
activation=leaky
|
300 |
+
|
301 |
+
[convolutional]
|
302 |
+
batch_normalize=1
|
303 |
+
filters=128
|
304 |
+
size=3
|
305 |
+
stride=1
|
306 |
+
pad=1
|
307 |
+
activation=leaky
|
308 |
+
|
309 |
+
[convolutional]
|
310 |
+
batch_normalize=1
|
311 |
+
filters=512
|
312 |
+
size=1
|
313 |
+
stride=1
|
314 |
+
pad=1
|
315 |
+
activation=linear
|
316 |
+
|
317 |
+
[shortcut]
|
318 |
+
from=-4
|
319 |
+
activation=leaky
|
320 |
+
|
321 |
+
[convolutional]
|
322 |
+
batch_normalize=1
|
323 |
+
filters=128
|
324 |
+
size=1
|
325 |
+
stride=1
|
326 |
+
pad=1
|
327 |
+
activation=leaky
|
328 |
+
|
329 |
+
[convolutional]
|
330 |
+
batch_normalize=1
|
331 |
+
filters=128
|
332 |
+
size=3
|
333 |
+
stride=1
|
334 |
+
pad=1
|
335 |
+
activation=leaky
|
336 |
+
|
337 |
+
[convolutional]
|
338 |
+
batch_normalize=1
|
339 |
+
filters=512
|
340 |
+
size=1
|
341 |
+
stride=1
|
342 |
+
pad=1
|
343 |
+
activation=linear
|
344 |
+
|
345 |
+
[shortcut]
|
346 |
+
from=-4
|
347 |
+
activation=leaky
|
348 |
+
|
349 |
+
|
350 |
+
# Conv 4
|
351 |
+
[convolutional]
|
352 |
+
batch_normalize=1
|
353 |
+
filters=256
|
354 |
+
size=1
|
355 |
+
stride=1
|
356 |
+
pad=1
|
357 |
+
activation=leaky
|
358 |
+
|
359 |
+
[convolutional]
|
360 |
+
batch_normalize=1
|
361 |
+
filters=256
|
362 |
+
size=3
|
363 |
+
stride=2
|
364 |
+
pad=1
|
365 |
+
activation=leaky
|
366 |
+
|
367 |
+
[convolutional]
|
368 |
+
batch_normalize=1
|
369 |
+
filters=1024
|
370 |
+
size=1
|
371 |
+
stride=1
|
372 |
+
pad=1
|
373 |
+
activation=linear
|
374 |
+
|
375 |
+
[shortcut]
|
376 |
+
from=-4
|
377 |
+
activation=leaky
|
378 |
+
|
379 |
+
[convolutional]
|
380 |
+
batch_normalize=1
|
381 |
+
filters=256
|
382 |
+
size=1
|
383 |
+
stride=1
|
384 |
+
pad=1
|
385 |
+
activation=leaky
|
386 |
+
|
387 |
+
[convolutional]
|
388 |
+
batch_normalize=1
|
389 |
+
filters=256
|
390 |
+
size=3
|
391 |
+
stride=1
|
392 |
+
pad=1
|
393 |
+
activation=leaky
|
394 |
+
|
395 |
+
[convolutional]
|
396 |
+
batch_normalize=1
|
397 |
+
filters=1024
|
398 |
+
size=1
|
399 |
+
stride=1
|
400 |
+
pad=1
|
401 |
+
activation=linear
|
402 |
+
|
403 |
+
[shortcut]
|
404 |
+
from=-4
|
405 |
+
activation=leaky
|
406 |
+
|
407 |
+
[convolutional]
|
408 |
+
batch_normalize=1
|
409 |
+
filters=256
|
410 |
+
size=1
|
411 |
+
stride=1
|
412 |
+
pad=1
|
413 |
+
activation=leaky
|
414 |
+
|
415 |
+
[convolutional]
|
416 |
+
batch_normalize=1
|
417 |
+
filters=256
|
418 |
+
size=3
|
419 |
+
stride=1
|
420 |
+
pad=1
|
421 |
+
activation=leaky
|
422 |
+
|
423 |
+
[convolutional]
|
424 |
+
batch_normalize=1
|
425 |
+
filters=1024
|
426 |
+
size=1
|
427 |
+
stride=1
|
428 |
+
pad=1
|
429 |
+
activation=linear
|
430 |
+
|
431 |
+
[shortcut]
|
432 |
+
from=-4
|
433 |
+
activation=leaky
|
434 |
+
|
435 |
+
[convolutional]
|
436 |
+
batch_normalize=1
|
437 |
+
filters=256
|
438 |
+
size=1
|
439 |
+
stride=1
|
440 |
+
pad=1
|
441 |
+
activation=leaky
|
442 |
+
|
443 |
+
[convolutional]
|
444 |
+
batch_normalize=1
|
445 |
+
filters=256
|
446 |
+
size=3
|
447 |
+
stride=1
|
448 |
+
pad=1
|
449 |
+
activation=leaky
|
450 |
+
|
451 |
+
[convolutional]
|
452 |
+
batch_normalize=1
|
453 |
+
filters=1024
|
454 |
+
size=1
|
455 |
+
stride=1
|
456 |
+
pad=1
|
457 |
+
activation=linear
|
458 |
+
|
459 |
+
[shortcut]
|
460 |
+
from=-4
|
461 |
+
activation=leaky
|
462 |
+
|
463 |
+
[convolutional]
|
464 |
+
batch_normalize=1
|
465 |
+
filters=256
|
466 |
+
size=1
|
467 |
+
stride=1
|
468 |
+
pad=1
|
469 |
+
activation=leaky
|
470 |
+
|
471 |
+
[convolutional]
|
472 |
+
batch_normalize=1
|
473 |
+
filters=256
|
474 |
+
size=3
|
475 |
+
stride=1
|
476 |
+
pad=1
|
477 |
+
activation=leaky
|
478 |
+
|
479 |
+
[convolutional]
|
480 |
+
batch_normalize=1
|
481 |
+
filters=1024
|
482 |
+
size=1
|
483 |
+
stride=1
|
484 |
+
pad=1
|
485 |
+
activation=linear
|
486 |
+
|
487 |
+
[shortcut]
|
488 |
+
from=-4
|
489 |
+
activation=leaky
|
490 |
+
|
491 |
+
[convolutional]
|
492 |
+
batch_normalize=1
|
493 |
+
filters=256
|
494 |
+
size=1
|
495 |
+
stride=1
|
496 |
+
pad=1
|
497 |
+
activation=leaky
|
498 |
+
|
499 |
+
[convolutional]
|
500 |
+
batch_normalize=1
|
501 |
+
filters=256
|
502 |
+
size=3
|
503 |
+
stride=1
|
504 |
+
pad=1
|
505 |
+
activation=leaky
|
506 |
+
|
507 |
+
[convolutional]
|
508 |
+
batch_normalize=1
|
509 |
+
filters=1024
|
510 |
+
size=1
|
511 |
+
stride=1
|
512 |
+
pad=1
|
513 |
+
activation=linear
|
514 |
+
|
515 |
+
[shortcut]
|
516 |
+
from=-4
|
517 |
+
activation=leaky
|
518 |
+
|
519 |
+
[convolutional]
|
520 |
+
batch_normalize=1
|
521 |
+
filters=256
|
522 |
+
size=1
|
523 |
+
stride=1
|
524 |
+
pad=1
|
525 |
+
activation=leaky
|
526 |
+
|
527 |
+
[convolutional]
|
528 |
+
batch_normalize=1
|
529 |
+
filters=256
|
530 |
+
size=3
|
531 |
+
stride=1
|
532 |
+
pad=1
|
533 |
+
activation=leaky
|
534 |
+
|
535 |
+
[convolutional]
|
536 |
+
batch_normalize=1
|
537 |
+
filters=1024
|
538 |
+
size=1
|
539 |
+
stride=1
|
540 |
+
pad=1
|
541 |
+
activation=linear
|
542 |
+
|
543 |
+
[shortcut]
|
544 |
+
from=-4
|
545 |
+
activation=leaky
|
546 |
+
|
547 |
+
[convolutional]
|
548 |
+
batch_normalize=1
|
549 |
+
filters=256
|
550 |
+
size=1
|
551 |
+
stride=1
|
552 |
+
pad=1
|
553 |
+
activation=leaky
|
554 |
+
|
555 |
+
[convolutional]
|
556 |
+
batch_normalize=1
|
557 |
+
filters=256
|
558 |
+
size=3
|
559 |
+
stride=1
|
560 |
+
pad=1
|
561 |
+
activation=leaky
|
562 |
+
|
563 |
+
[convolutional]
|
564 |
+
batch_normalize=1
|
565 |
+
filters=1024
|
566 |
+
size=1
|
567 |
+
stride=1
|
568 |
+
pad=1
|
569 |
+
activation=linear
|
570 |
+
|
571 |
+
[shortcut]
|
572 |
+
from=-4
|
573 |
+
activation=leaky
|
574 |
+
|
575 |
+
[convolutional]
|
576 |
+
batch_normalize=1
|
577 |
+
filters=256
|
578 |
+
size=1
|
579 |
+
stride=1
|
580 |
+
pad=1
|
581 |
+
activation=leaky
|
582 |
+
|
583 |
+
[convolutional]
|
584 |
+
batch_normalize=1
|
585 |
+
filters=256
|
586 |
+
size=3
|
587 |
+
stride=1
|
588 |
+
pad=1
|
589 |
+
activation=leaky
|
590 |
+
|
591 |
+
[convolutional]
|
592 |
+
batch_normalize=1
|
593 |
+
filters=1024
|
594 |
+
size=1
|
595 |
+
stride=1
|
596 |
+
pad=1
|
597 |
+
activation=linear
|
598 |
+
|
599 |
+
[shortcut]
|
600 |
+
from=-4
|
601 |
+
activation=leaky
|
602 |
+
|
603 |
+
[convolutional]
|
604 |
+
batch_normalize=1
|
605 |
+
filters=256
|
606 |
+
size=1
|
607 |
+
stride=1
|
608 |
+
pad=1
|
609 |
+
activation=leaky
|
610 |
+
|
611 |
+
[convolutional]
|
612 |
+
batch_normalize=1
|
613 |
+
filters=256
|
614 |
+
size=3
|
615 |
+
stride=1
|
616 |
+
pad=1
|
617 |
+
activation=leaky
|
618 |
+
|
619 |
+
[convolutional]
|
620 |
+
batch_normalize=1
|
621 |
+
filters=1024
|
622 |
+
size=1
|
623 |
+
stride=1
|
624 |
+
pad=1
|
625 |
+
activation=linear
|
626 |
+
|
627 |
+
[shortcut]
|
628 |
+
from=-4
|
629 |
+
activation=leaky
|
630 |
+
|
631 |
+
[convolutional]
|
632 |
+
batch_normalize=1
|
633 |
+
filters=256
|
634 |
+
size=1
|
635 |
+
stride=1
|
636 |
+
pad=1
|
637 |
+
activation=leaky
|
638 |
+
|
639 |
+
[convolutional]
|
640 |
+
batch_normalize=1
|
641 |
+
filters=256
|
642 |
+
size=3
|
643 |
+
stride=1
|
644 |
+
pad=1
|
645 |
+
activation=leaky
|
646 |
+
|
647 |
+
[convolutional]
|
648 |
+
batch_normalize=1
|
649 |
+
filters=1024
|
650 |
+
size=1
|
651 |
+
stride=1
|
652 |
+
pad=1
|
653 |
+
activation=linear
|
654 |
+
|
655 |
+
[shortcut]
|
656 |
+
from=-4
|
657 |
+
activation=leaky
|
658 |
+
|
659 |
+
[convolutional]
|
660 |
+
batch_normalize=1
|
661 |
+
filters=256
|
662 |
+
size=1
|
663 |
+
stride=1
|
664 |
+
pad=1
|
665 |
+
activation=leaky
|
666 |
+
|
667 |
+
[convolutional]
|
668 |
+
batch_normalize=1
|
669 |
+
filters=256
|
670 |
+
size=3
|
671 |
+
stride=1
|
672 |
+
pad=1
|
673 |
+
activation=leaky
|
674 |
+
|
675 |
+
[convolutional]
|
676 |
+
batch_normalize=1
|
677 |
+
filters=1024
|
678 |
+
size=1
|
679 |
+
stride=1
|
680 |
+
pad=1
|
681 |
+
activation=linear
|
682 |
+
|
683 |
+
[shortcut]
|
684 |
+
from=-4
|
685 |
+
activation=leaky
|
686 |
+
|
687 |
+
[convolutional]
|
688 |
+
batch_normalize=1
|
689 |
+
filters=256
|
690 |
+
size=1
|
691 |
+
stride=1
|
692 |
+
pad=1
|
693 |
+
activation=leaky
|
694 |
+
|
695 |
+
[convolutional]
|
696 |
+
batch_normalize=1
|
697 |
+
filters=256
|
698 |
+
size=3
|
699 |
+
stride=1
|
700 |
+
pad=1
|
701 |
+
activation=leaky
|
702 |
+
|
703 |
+
[convolutional]
|
704 |
+
batch_normalize=1
|
705 |
+
filters=1024
|
706 |
+
size=1
|
707 |
+
stride=1
|
708 |
+
pad=1
|
709 |
+
activation=linear
|
710 |
+
|
711 |
+
[shortcut]
|
712 |
+
from=-4
|
713 |
+
activation=leaky
|
714 |
+
|
715 |
+
[convolutional]
|
716 |
+
batch_normalize=1
|
717 |
+
filters=256
|
718 |
+
size=1
|
719 |
+
stride=1
|
720 |
+
pad=1
|
721 |
+
activation=leaky
|
722 |
+
|
723 |
+
[convolutional]
|
724 |
+
batch_normalize=1
|
725 |
+
filters=256
|
726 |
+
size=3
|
727 |
+
stride=1
|
728 |
+
pad=1
|
729 |
+
activation=leaky
|
730 |
+
|
731 |
+
[convolutional]
|
732 |
+
batch_normalize=1
|
733 |
+
filters=1024
|
734 |
+
size=1
|
735 |
+
stride=1
|
736 |
+
pad=1
|
737 |
+
activation=linear
|
738 |
+
|
739 |
+
[shortcut]
|
740 |
+
from=-4
|
741 |
+
activation=leaky
|
742 |
+
|
743 |
+
[convolutional]
|
744 |
+
batch_normalize=1
|
745 |
+
filters=256
|
746 |
+
size=1
|
747 |
+
stride=1
|
748 |
+
pad=1
|
749 |
+
activation=leaky
|
750 |
+
|
751 |
+
[convolutional]
|
752 |
+
batch_normalize=1
|
753 |
+
filters=256
|
754 |
+
size=3
|
755 |
+
stride=1
|
756 |
+
pad=1
|
757 |
+
activation=leaky
|
758 |
+
|
759 |
+
[convolutional]
|
760 |
+
batch_normalize=1
|
761 |
+
filters=1024
|
762 |
+
size=1
|
763 |
+
stride=1
|
764 |
+
pad=1
|
765 |
+
activation=linear
|
766 |
+
|
767 |
+
[shortcut]
|
768 |
+
from=-4
|
769 |
+
activation=leaky
|
770 |
+
|
771 |
+
[convolutional]
|
772 |
+
batch_normalize=1
|
773 |
+
filters=256
|
774 |
+
size=1
|
775 |
+
stride=1
|
776 |
+
pad=1
|
777 |
+
activation=leaky
|
778 |
+
|
779 |
+
[convolutional]
|
780 |
+
batch_normalize=1
|
781 |
+
filters=256
|
782 |
+
size=3
|
783 |
+
stride=1
|
784 |
+
pad=1
|
785 |
+
activation=leaky
|
786 |
+
|
787 |
+
[convolutional]
|
788 |
+
batch_normalize=1
|
789 |
+
filters=1024
|
790 |
+
size=1
|
791 |
+
stride=1
|
792 |
+
pad=1
|
793 |
+
activation=linear
|
794 |
+
|
795 |
+
[shortcut]
|
796 |
+
from=-4
|
797 |
+
activation=leaky
|
798 |
+
|
799 |
+
[convolutional]
|
800 |
+
batch_normalize=1
|
801 |
+
filters=256
|
802 |
+
size=1
|
803 |
+
stride=1
|
804 |
+
pad=1
|
805 |
+
activation=leaky
|
806 |
+
|
807 |
+
[convolutional]
|
808 |
+
batch_normalize=1
|
809 |
+
filters=256
|
810 |
+
size=3
|
811 |
+
stride=1
|
812 |
+
pad=1
|
813 |
+
activation=leaky
|
814 |
+
|
815 |
+
[convolutional]
|
816 |
+
batch_normalize=1
|
817 |
+
filters=1024
|
818 |
+
size=1
|
819 |
+
stride=1
|
820 |
+
pad=1
|
821 |
+
activation=linear
|
822 |
+
|
823 |
+
[shortcut]
|
824 |
+
from=-4
|
825 |
+
activation=leaky
|
826 |
+
|
827 |
+
[convolutional]
|
828 |
+
batch_normalize=1
|
829 |
+
filters=256
|
830 |
+
size=1
|
831 |
+
stride=1
|
832 |
+
pad=1
|
833 |
+
activation=leaky
|
834 |
+
|
835 |
+
[convolutional]
|
836 |
+
batch_normalize=1
|
837 |
+
filters=256
|
838 |
+
size=3
|
839 |
+
stride=1
|
840 |
+
pad=1
|
841 |
+
activation=leaky
|
842 |
+
|
843 |
+
[convolutional]
|
844 |
+
batch_normalize=1
|
845 |
+
filters=1024
|
846 |
+
size=1
|
847 |
+
stride=1
|
848 |
+
pad=1
|
849 |
+
activation=linear
|
850 |
+
|
851 |
+
[shortcut]
|
852 |
+
from=-4
|
853 |
+
activation=leaky
|
854 |
+
|
855 |
+
[convolutional]
|
856 |
+
batch_normalize=1
|
857 |
+
filters=256
|
858 |
+
size=1
|
859 |
+
stride=1
|
860 |
+
pad=1
|
861 |
+
activation=leaky
|
862 |
+
|
863 |
+
[convolutional]
|
864 |
+
batch_normalize=1
|
865 |
+
filters=256
|
866 |
+
size=3
|
867 |
+
stride=1
|
868 |
+
pad=1
|
869 |
+
activation=leaky
|
870 |
+
|
871 |
+
[convolutional]
|
872 |
+
batch_normalize=1
|
873 |
+
filters=1024
|
874 |
+
size=1
|
875 |
+
stride=1
|
876 |
+
pad=1
|
877 |
+
activation=linear
|
878 |
+
|
879 |
+
[shortcut]
|
880 |
+
from=-4
|
881 |
+
activation=leaky
|
882 |
+
|
883 |
+
[convolutional]
|
884 |
+
batch_normalize=1
|
885 |
+
filters=256
|
886 |
+
size=1
|
887 |
+
stride=1
|
888 |
+
pad=1
|
889 |
+
activation=leaky
|
890 |
+
|
891 |
+
[convolutional]
|
892 |
+
batch_normalize=1
|
893 |
+
filters=256
|
894 |
+
size=3
|
895 |
+
stride=1
|
896 |
+
pad=1
|
897 |
+
activation=leaky
|
898 |
+
|
899 |
+
[convolutional]
|
900 |
+
batch_normalize=1
|
901 |
+
filters=1024
|
902 |
+
size=1
|
903 |
+
stride=1
|
904 |
+
pad=1
|
905 |
+
activation=linear
|
906 |
+
|
907 |
+
[shortcut]
|
908 |
+
from=-4
|
909 |
+
activation=leaky
|
910 |
+
|
911 |
+
[convolutional]
|
912 |
+
batch_normalize=1
|
913 |
+
filters=256
|
914 |
+
size=1
|
915 |
+
stride=1
|
916 |
+
pad=1
|
917 |
+
activation=leaky
|
918 |
+
|
919 |
+
[convolutional]
|
920 |
+
batch_normalize=1
|
921 |
+
filters=256
|
922 |
+
size=3
|
923 |
+
stride=1
|
924 |
+
pad=1
|
925 |
+
activation=leaky
|
926 |
+
|
927 |
+
[convolutional]
|
928 |
+
batch_normalize=1
|
929 |
+
filters=1024
|
930 |
+
size=1
|
931 |
+
stride=1
|
932 |
+
pad=1
|
933 |
+
activation=linear
|
934 |
+
|
935 |
+
[shortcut]
|
936 |
+
from=-4
|
937 |
+
activation=leaky
|
938 |
+
|
939 |
+
[convolutional]
|
940 |
+
batch_normalize=1
|
941 |
+
filters=256
|
942 |
+
size=1
|
943 |
+
stride=1
|
944 |
+
pad=1
|
945 |
+
activation=leaky
|
946 |
+
|
947 |
+
[convolutional]
|
948 |
+
batch_normalize=1
|
949 |
+
filters=256
|
950 |
+
size=3
|
951 |
+
stride=1
|
952 |
+
pad=1
|
953 |
+
activation=leaky
|
954 |
+
|
955 |
+
[convolutional]
|
956 |
+
batch_normalize=1
|
957 |
+
filters=1024
|
958 |
+
size=1
|
959 |
+
stride=1
|
960 |
+
pad=1
|
961 |
+
activation=linear
|
962 |
+
|
963 |
+
[shortcut]
|
964 |
+
from=-4
|
965 |
+
activation=leaky
|
966 |
+
|
967 |
+
[convolutional]
|
968 |
+
batch_normalize=1
|
969 |
+
filters=256
|
970 |
+
size=1
|
971 |
+
stride=1
|
972 |
+
pad=1
|
973 |
+
activation=leaky
|
974 |
+
|
975 |
+
[convolutional]
|
976 |
+
batch_normalize=1
|
977 |
+
filters=256
|
978 |
+
size=3
|
979 |
+
stride=1
|
980 |
+
pad=1
|
981 |
+
activation=leaky
|
982 |
+
|
983 |
+
[convolutional]
|
984 |
+
batch_normalize=1
|
985 |
+
filters=1024
|
986 |
+
size=1
|
987 |
+
stride=1
|
988 |
+
pad=1
|
989 |
+
activation=linear
|
990 |
+
|
991 |
+
[shortcut]
|
992 |
+
from=-4
|
993 |
+
activation=leaky
|
994 |
+
|
995 |
+
[convolutional]
|
996 |
+
batch_normalize=1
|
997 |
+
filters=256
|
998 |
+
size=1
|
999 |
+
stride=1
|
1000 |
+
pad=1
|
1001 |
+
activation=leaky
|
1002 |
+
|
1003 |
+
[convolutional]
|
1004 |
+
batch_normalize=1
|
1005 |
+
filters=256
|
1006 |
+
size=3
|
1007 |
+
stride=1
|
1008 |
+
pad=1
|
1009 |
+
activation=leaky
|
1010 |
+
|
1011 |
+
[convolutional]
|
1012 |
+
batch_normalize=1
|
1013 |
+
filters=1024
|
1014 |
+
size=1
|
1015 |
+
stride=1
|
1016 |
+
pad=1
|
1017 |
+
activation=linear
|
1018 |
+
|
1019 |
+
[shortcut]
|
1020 |
+
from=-4
|
1021 |
+
activation=leaky
|
1022 |
+
|
1023 |
+
[convolutional]
|
1024 |
+
batch_normalize=1
|
1025 |
+
filters=256
|
1026 |
+
size=1
|
1027 |
+
stride=1
|
1028 |
+
pad=1
|
1029 |
+
activation=leaky
|
1030 |
+
|
1031 |
+
[convolutional]
|
1032 |
+
batch_normalize=1
|
1033 |
+
filters=256
|
1034 |
+
size=3
|
1035 |
+
stride=1
|
1036 |
+
pad=1
|
1037 |
+
activation=leaky
|
1038 |
+
|
1039 |
+
[convolutional]
|
1040 |
+
batch_normalize=1
|
1041 |
+
filters=1024
|
1042 |
+
size=1
|
1043 |
+
stride=1
|
1044 |
+
pad=1
|
1045 |
+
activation=linear
|
1046 |
+
|
1047 |
+
[shortcut]
|
1048 |
+
from=-4
|
1049 |
+
activation=leaky
|
1050 |
+
|
1051 |
+
[convolutional]
|
1052 |
+
batch_normalize=1
|
1053 |
+
filters=256
|
1054 |
+
size=1
|
1055 |
+
stride=1
|
1056 |
+
pad=1
|
1057 |
+
activation=leaky
|
1058 |
+
|
1059 |
+
[convolutional]
|
1060 |
+
batch_normalize=1
|
1061 |
+
filters=256
|
1062 |
+
size=3
|
1063 |
+
stride=1
|
1064 |
+
pad=1
|
1065 |
+
activation=leaky
|
1066 |
+
|
1067 |
+
[convolutional]
|
1068 |
+
batch_normalize=1
|
1069 |
+
filters=1024
|
1070 |
+
size=1
|
1071 |
+
stride=1
|
1072 |
+
pad=1
|
1073 |
+
activation=linear
|
1074 |
+
|
1075 |
+
[shortcut]
|
1076 |
+
from=-4
|
1077 |
+
activation=leaky
|
1078 |
+
|
1079 |
+
[convolutional]
|
1080 |
+
batch_normalize=1
|
1081 |
+
filters=256
|
1082 |
+
size=1
|
1083 |
+
stride=1
|
1084 |
+
pad=1
|
1085 |
+
activation=leaky
|
1086 |
+
|
1087 |
+
[convolutional]
|
1088 |
+
batch_normalize=1
|
1089 |
+
filters=256
|
1090 |
+
size=3
|
1091 |
+
stride=1
|
1092 |
+
pad=1
|
1093 |
+
activation=leaky
|
1094 |
+
|
1095 |
+
[convolutional]
|
1096 |
+
batch_normalize=1
|
1097 |
+
filters=1024
|
1098 |
+
size=1
|
1099 |
+
stride=1
|
1100 |
+
pad=1
|
1101 |
+
activation=linear
|
1102 |
+
|
1103 |
+
[shortcut]
|
1104 |
+
from=-4
|
1105 |
+
activation=leaky
|
1106 |
+
|
1107 |
+
[convolutional]
|
1108 |
+
batch_normalize=1
|
1109 |
+
filters=256
|
1110 |
+
size=1
|
1111 |
+
stride=1
|
1112 |
+
pad=1
|
1113 |
+
activation=leaky
|
1114 |
+
|
1115 |
+
[convolutional]
|
1116 |
+
batch_normalize=1
|
1117 |
+
filters=256
|
1118 |
+
size=3
|
1119 |
+
stride=1
|
1120 |
+
pad=1
|
1121 |
+
activation=leaky
|
1122 |
+
|
1123 |
+
[convolutional]
|
1124 |
+
batch_normalize=1
|
1125 |
+
filters=1024
|
1126 |
+
size=1
|
1127 |
+
stride=1
|
1128 |
+
pad=1
|
1129 |
+
activation=linear
|
1130 |
+
|
1131 |
+
[shortcut]
|
1132 |
+
from=-4
|
1133 |
+
activation=leaky
|
1134 |
+
|
1135 |
+
[convolutional]
|
1136 |
+
batch_normalize=1
|
1137 |
+
filters=256
|
1138 |
+
size=1
|
1139 |
+
stride=1
|
1140 |
+
pad=1
|
1141 |
+
activation=leaky
|
1142 |
+
|
1143 |
+
[convolutional]
|
1144 |
+
batch_normalize=1
|
1145 |
+
filters=256
|
1146 |
+
size=3
|
1147 |
+
stride=1
|
1148 |
+
pad=1
|
1149 |
+
activation=leaky
|
1150 |
+
|
1151 |
+
[convolutional]
|
1152 |
+
batch_normalize=1
|
1153 |
+
filters=1024
|
1154 |
+
size=1
|
1155 |
+
stride=1
|
1156 |
+
pad=1
|
1157 |
+
activation=linear
|
1158 |
+
|
1159 |
+
[shortcut]
|
1160 |
+
from=-4
|
1161 |
+
activation=leaky
|
1162 |
+
|
1163 |
+
[convolutional]
|
1164 |
+
batch_normalize=1
|
1165 |
+
filters=256
|
1166 |
+
size=1
|
1167 |
+
stride=1
|
1168 |
+
pad=1
|
1169 |
+
activation=leaky
|
1170 |
+
|
1171 |
+
[convolutional]
|
1172 |
+
batch_normalize=1
|
1173 |
+
filters=256
|
1174 |
+
size=3
|
1175 |
+
stride=1
|
1176 |
+
pad=1
|
1177 |
+
activation=leaky
|
1178 |
+
|
1179 |
+
[convolutional]
|
1180 |
+
batch_normalize=1
|
1181 |
+
filters=1024
|
1182 |
+
size=1
|
1183 |
+
stride=1
|
1184 |
+
pad=1
|
1185 |
+
activation=linear
|
1186 |
+
|
1187 |
+
[shortcut]
|
1188 |
+
from=-4
|
1189 |
+
activation=leaky
|
1190 |
+
|
1191 |
+
[convolutional]
|
1192 |
+
batch_normalize=1
|
1193 |
+
filters=256
|
1194 |
+
size=1
|
1195 |
+
stride=1
|
1196 |
+
pad=1
|
1197 |
+
activation=leaky
|
1198 |
+
|
1199 |
+
[convolutional]
|
1200 |
+
batch_normalize=1
|
1201 |
+
filters=256
|
1202 |
+
size=3
|
1203 |
+
stride=1
|
1204 |
+
pad=1
|
1205 |
+
activation=leaky
|
1206 |
+
|
1207 |
+
[convolutional]
|
1208 |
+
batch_normalize=1
|
1209 |
+
filters=1024
|
1210 |
+
size=1
|
1211 |
+
stride=1
|
1212 |
+
pad=1
|
1213 |
+
activation=linear
|
1214 |
+
|
1215 |
+
[shortcut]
|
1216 |
+
from=-4
|
1217 |
+
activation=leaky
|
1218 |
+
|
1219 |
+
[convolutional]
|
1220 |
+
batch_normalize=1
|
1221 |
+
filters=256
|
1222 |
+
size=1
|
1223 |
+
stride=1
|
1224 |
+
pad=1
|
1225 |
+
activation=leaky
|
1226 |
+
|
1227 |
+
[convolutional]
|
1228 |
+
batch_normalize=1
|
1229 |
+
filters=256
|
1230 |
+
size=3
|
1231 |
+
stride=1
|
1232 |
+
pad=1
|
1233 |
+
activation=leaky
|
1234 |
+
|
1235 |
+
[convolutional]
|
1236 |
+
batch_normalize=1
|
1237 |
+
filters=1024
|
1238 |
+
size=1
|
1239 |
+
stride=1
|
1240 |
+
pad=1
|
1241 |
+
activation=linear
|
1242 |
+
|
1243 |
+
[shortcut]
|
1244 |
+
from=-4
|
1245 |
+
activation=leaky
|
1246 |
+
|
1247 |
+
[convolutional]
|
1248 |
+
batch_normalize=1
|
1249 |
+
filters=256
|
1250 |
+
size=1
|
1251 |
+
stride=1
|
1252 |
+
pad=1
|
1253 |
+
activation=leaky
|
1254 |
+
|
1255 |
+
[convolutional]
|
1256 |
+
batch_normalize=1
|
1257 |
+
filters=256
|
1258 |
+
size=3
|
1259 |
+
stride=1
|
1260 |
+
pad=1
|
1261 |
+
activation=leaky
|
1262 |
+
|
1263 |
+
[convolutional]
|
1264 |
+
batch_normalize=1
|
1265 |
+
filters=1024
|
1266 |
+
size=1
|
1267 |
+
stride=1
|
1268 |
+
pad=1
|
1269 |
+
activation=linear
|
1270 |
+
|
1271 |
+
[shortcut]
|
1272 |
+
from=-4
|
1273 |
+
activation=leaky
|
1274 |
+
|
1275 |
+
[convolutional]
|
1276 |
+
batch_normalize=1
|
1277 |
+
filters=256
|
1278 |
+
size=1
|
1279 |
+
stride=1
|
1280 |
+
pad=1
|
1281 |
+
activation=leaky
|
1282 |
+
|
1283 |
+
[convolutional]
|
1284 |
+
batch_normalize=1
|
1285 |
+
filters=256
|
1286 |
+
size=3
|
1287 |
+
stride=1
|
1288 |
+
pad=1
|
1289 |
+
activation=leaky
|
1290 |
+
|
1291 |
+
[convolutional]
|
1292 |
+
batch_normalize=1
|
1293 |
+
filters=1024
|
1294 |
+
size=1
|
1295 |
+
stride=1
|
1296 |
+
pad=1
|
1297 |
+
activation=linear
|
1298 |
+
|
1299 |
+
[shortcut]
|
1300 |
+
from=-4
|
1301 |
+
activation=leaky
|
1302 |
+
|
1303 |
+
[convolutional]
|
1304 |
+
batch_normalize=1
|
1305 |
+
filters=256
|
1306 |
+
size=1
|
1307 |
+
stride=1
|
1308 |
+
pad=1
|
1309 |
+
activation=leaky
|
1310 |
+
|
1311 |
+
[convolutional]
|
1312 |
+
batch_normalize=1
|
1313 |
+
filters=256
|
1314 |
+
size=3
|
1315 |
+
stride=1
|
1316 |
+
pad=1
|
1317 |
+
activation=leaky
|
1318 |
+
|
1319 |
+
[convolutional]
|
1320 |
+
batch_normalize=1
|
1321 |
+
filters=1024
|
1322 |
+
size=1
|
1323 |
+
stride=1
|
1324 |
+
pad=1
|
1325 |
+
activation=linear
|
1326 |
+
|
1327 |
+
[shortcut]
|
1328 |
+
from=-4
|
1329 |
+
activation=leaky
|
1330 |
+
|
1331 |
+
[convolutional]
|
1332 |
+
batch_normalize=1
|
1333 |
+
filters=256
|
1334 |
+
size=1
|
1335 |
+
stride=1
|
1336 |
+
pad=1
|
1337 |
+
activation=leaky
|
1338 |
+
|
1339 |
+
[convolutional]
|
1340 |
+
batch_normalize=1
|
1341 |
+
filters=256
|
1342 |
+
size=3
|
1343 |
+
stride=1
|
1344 |
+
pad=1
|
1345 |
+
activation=leaky
|
1346 |
+
|
1347 |
+
[convolutional]
|
1348 |
+
batch_normalize=1
|
1349 |
+
filters=1024
|
1350 |
+
size=1
|
1351 |
+
stride=1
|
1352 |
+
pad=1
|
1353 |
+
activation=linear
|
1354 |
+
|
1355 |
+
[shortcut]
|
1356 |
+
from=-4
|
1357 |
+
activation=leaky
|
1358 |
+
|
1359 |
+
#Conv 5
|
1360 |
+
[convolutional]
|
1361 |
+
batch_normalize=1
|
1362 |
+
filters=512
|
1363 |
+
size=1
|
1364 |
+
stride=1
|
1365 |
+
pad=1
|
1366 |
+
activation=leaky
|
1367 |
+
|
1368 |
+
[convolutional]
|
1369 |
+
batch_normalize=1
|
1370 |
+
filters=512
|
1371 |
+
size=3
|
1372 |
+
stride=2
|
1373 |
+
pad=1
|
1374 |
+
activation=leaky
|
1375 |
+
|
1376 |
+
[convolutional]
|
1377 |
+
batch_normalize=1
|
1378 |
+
filters=2048
|
1379 |
+
size=1
|
1380 |
+
stride=1
|
1381 |
+
pad=1
|
1382 |
+
activation=linear
|
1383 |
+
|
1384 |
+
[shortcut]
|
1385 |
+
from=-4
|
1386 |
+
activation=leaky
|
1387 |
+
|
1388 |
+
[convolutional]
|
1389 |
+
batch_normalize=1
|
1390 |
+
filters=512
|
1391 |
+
size=1
|
1392 |
+
stride=1
|
1393 |
+
pad=1
|
1394 |
+
activation=leaky
|
1395 |
+
|
1396 |
+
[convolutional]
|
1397 |
+
batch_normalize=1
|
1398 |
+
filters=512
|
1399 |
+
size=3
|
1400 |
+
stride=1
|
1401 |
+
pad=1
|
1402 |
+
activation=leaky
|
1403 |
+
|
1404 |
+
[convolutional]
|
1405 |
+
batch_normalize=1
|
1406 |
+
filters=2048
|
1407 |
+
size=1
|
1408 |
+
stride=1
|
1409 |
+
pad=1
|
1410 |
+
activation=linear
|
1411 |
+
|
1412 |
+
[shortcut]
|
1413 |
+
from=-4
|
1414 |
+
activation=leaky
|
1415 |
+
|
1416 |
+
[convolutional]
|
1417 |
+
batch_normalize=1
|
1418 |
+
filters=512
|
1419 |
+
size=1
|
1420 |
+
stride=1
|
1421 |
+
pad=1
|
1422 |
+
activation=leaky
|
1423 |
+
|
1424 |
+
[convolutional]
|
1425 |
+
batch_normalize=1
|
1426 |
+
filters=512
|
1427 |
+
size=3
|
1428 |
+
stride=1
|
1429 |
+
pad=1
|
1430 |
+
activation=leaky
|
1431 |
+
|
1432 |
+
[convolutional]
|
1433 |
+
batch_normalize=1
|
1434 |
+
filters=2048
|
1435 |
+
size=1
|
1436 |
+
stride=1
|
1437 |
+
pad=1
|
1438 |
+
activation=linear
|
1439 |
+
|
1440 |
+
[shortcut]
|
1441 |
+
from=-4
|
1442 |
+
activation=leaky
|
1443 |
+
|
1444 |
+
|
1445 |
+
|
1446 |
+
|
1447 |
+
|
1448 |
+
|
1449 |
+
[convolutional]
|
1450 |
+
filters=1000
|
1451 |
+
size=1
|
1452 |
+
stride=1
|
1453 |
+
pad=1
|
1454 |
+
activation=linear
|
1455 |
+
|
1456 |
+
[avgpool]
|
1457 |
+
|
1458 |
+
[softmax]
|
1459 |
+
groups=1
|
1460 |
+
|
model/cfg/resnet18.cfg
ADDED
@@ -0,0 +1,228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=1
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
channels=3
|
13 |
+
min_crop=128
|
14 |
+
max_crop=448
|
15 |
+
|
16 |
+
burn_in=1000
|
17 |
+
learning_rate=0.1
|
18 |
+
policy=poly
|
19 |
+
power=4
|
20 |
+
max_batches=800000
|
21 |
+
momentum=0.9
|
22 |
+
decay=0.0005
|
23 |
+
|
24 |
+
angle=7
|
25 |
+
hue=.1
|
26 |
+
saturation=.75
|
27 |
+
exposure=.75
|
28 |
+
aspect=.75
|
29 |
+
|
30 |
+
|
31 |
+
[convolutional]
|
32 |
+
batch_normalize=1
|
33 |
+
filters=64
|
34 |
+
size=7
|
35 |
+
stride=2
|
36 |
+
pad=1
|
37 |
+
activation=leaky
|
38 |
+
|
39 |
+
[maxpool]
|
40 |
+
size=2
|
41 |
+
stride=2
|
42 |
+
|
43 |
+
|
44 |
+
# Residual Block
|
45 |
+
[convolutional]
|
46 |
+
batch_normalize=1
|
47 |
+
filters=64
|
48 |
+
size=3
|
49 |
+
stride=1
|
50 |
+
pad=1
|
51 |
+
activation=leaky
|
52 |
+
|
53 |
+
[convolutional]
|
54 |
+
batch_normalize=1
|
55 |
+
filters=64
|
56 |
+
size=3
|
57 |
+
stride=1
|
58 |
+
pad=1
|
59 |
+
activation=linear
|
60 |
+
|
61 |
+
[shortcut]
|
62 |
+
activation=leaky
|
63 |
+
from=-3
|
64 |
+
|
65 |
+
# Residual Block
|
66 |
+
[convolutional]
|
67 |
+
batch_normalize=1
|
68 |
+
filters=64
|
69 |
+
size=3
|
70 |
+
stride=1
|
71 |
+
pad=1
|
72 |
+
activation=leaky
|
73 |
+
|
74 |
+
[convolutional]
|
75 |
+
batch_normalize=1
|
76 |
+
filters=64
|
77 |
+
size=3
|
78 |
+
stride=1
|
79 |
+
pad=1
|
80 |
+
activation=linear
|
81 |
+
|
82 |
+
[shortcut]
|
83 |
+
activation=leaky
|
84 |
+
from=-3
|
85 |
+
|
86 |
+
# Strided Residual Block
|
87 |
+
[convolutional]
|
88 |
+
batch_normalize=1
|
89 |
+
filters=128
|
90 |
+
size=3
|
91 |
+
stride=2
|
92 |
+
pad=1
|
93 |
+
activation=leaky
|
94 |
+
|
95 |
+
[convolutional]
|
96 |
+
batch_normalize=1
|
97 |
+
filters=128
|
98 |
+
size=3
|
99 |
+
stride=1
|
100 |
+
pad=1
|
101 |
+
activation=linear
|
102 |
+
|
103 |
+
[shortcut]
|
104 |
+
activation=leaky
|
105 |
+
from=-3
|
106 |
+
|
107 |
+
# Residual Block
|
108 |
+
[convolutional]
|
109 |
+
batch_normalize=1
|
110 |
+
filters=128
|
111 |
+
size=3
|
112 |
+
stride=1
|
113 |
+
pad=1
|
114 |
+
activation=leaky
|
115 |
+
|
116 |
+
[convolutional]
|
117 |
+
batch_normalize=1
|
118 |
+
filters=128
|
119 |
+
size=3
|
120 |
+
stride=1
|
121 |
+
pad=1
|
122 |
+
activation=linear
|
123 |
+
|
124 |
+
[shortcut]
|
125 |
+
activation=leaky
|
126 |
+
from=-3
|
127 |
+
|
128 |
+
|
129 |
+
# Strided Residual Block
|
130 |
+
[convolutional]
|
131 |
+
batch_normalize=1
|
132 |
+
filters=256
|
133 |
+
size=3
|
134 |
+
stride=2
|
135 |
+
pad=1
|
136 |
+
activation=leaky
|
137 |
+
|
138 |
+
[convolutional]
|
139 |
+
batch_normalize=1
|
140 |
+
filters=256
|
141 |
+
size=3
|
142 |
+
stride=1
|
143 |
+
pad=1
|
144 |
+
activation=linear
|
145 |
+
|
146 |
+
[shortcut]
|
147 |
+
activation=leaky
|
148 |
+
from=-3
|
149 |
+
|
150 |
+
# Residual Block
|
151 |
+
[convolutional]
|
152 |
+
batch_normalize=1
|
153 |
+
filters=256
|
154 |
+
size=3
|
155 |
+
stride=1
|
156 |
+
pad=1
|
157 |
+
activation=leaky
|
158 |
+
|
159 |
+
[convolutional]
|
160 |
+
batch_normalize=1
|
161 |
+
filters=256
|
162 |
+
size=3
|
163 |
+
stride=1
|
164 |
+
pad=1
|
165 |
+
activation=linear
|
166 |
+
|
167 |
+
[shortcut]
|
168 |
+
activation=leaky
|
169 |
+
from=-3
|
170 |
+
|
171 |
+
|
172 |
+
# Strided Residual Block
|
173 |
+
[convolutional]
|
174 |
+
batch_normalize=1
|
175 |
+
filters=512
|
176 |
+
size=3
|
177 |
+
stride=2
|
178 |
+
pad=1
|
179 |
+
activation=leaky
|
180 |
+
|
181 |
+
[convolutional]
|
182 |
+
batch_normalize=1
|
183 |
+
filters=512
|
184 |
+
size=3
|
185 |
+
stride=1
|
186 |
+
pad=1
|
187 |
+
activation=linear
|
188 |
+
|
189 |
+
[shortcut]
|
190 |
+
activation=leaky
|
191 |
+
from=-3
|
192 |
+
|
193 |
+
# Residual Block
|
194 |
+
[convolutional]
|
195 |
+
batch_normalize=1
|
196 |
+
filters=512
|
197 |
+
size=3
|
198 |
+
stride=1
|
199 |
+
pad=1
|
200 |
+
activation=leaky
|
201 |
+
|
202 |
+
[convolutional]
|
203 |
+
batch_normalize=1
|
204 |
+
filters=512
|
205 |
+
size=3
|
206 |
+
stride=1
|
207 |
+
pad=1
|
208 |
+
activation=linear
|
209 |
+
|
210 |
+
[shortcut]
|
211 |
+
activation=leaky
|
212 |
+
from=-3
|
213 |
+
|
214 |
+
|
215 |
+
|
216 |
+
|
217 |
+
[avgpool]
|
218 |
+
|
219 |
+
[convolutional]
|
220 |
+
filters=1000
|
221 |
+
size=1
|
222 |
+
stride=1
|
223 |
+
pad=1
|
224 |
+
activation=linear
|
225 |
+
|
226 |
+
[softmax]
|
227 |
+
groups=1
|
228 |
+
|
model/cfg/resnet34.cfg
ADDED
@@ -0,0 +1,392 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=2
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
channels=3
|
13 |
+
min_crop=128
|
14 |
+
max_crop=448
|
15 |
+
|
16 |
+
burn_in=1000
|
17 |
+
learning_rate=0.1
|
18 |
+
policy=poly
|
19 |
+
power=4
|
20 |
+
max_batches=800000
|
21 |
+
momentum=0.9
|
22 |
+
decay=0.0005
|
23 |
+
|
24 |
+
angle=7
|
25 |
+
hue=.1
|
26 |
+
saturation=.75
|
27 |
+
exposure=.75
|
28 |
+
aspect=.75
|
29 |
+
|
30 |
+
|
31 |
+
[convolutional]
|
32 |
+
batch_normalize=1
|
33 |
+
filters=64
|
34 |
+
size=7
|
35 |
+
stride=2
|
36 |
+
pad=1
|
37 |
+
activation=leaky
|
38 |
+
|
39 |
+
[maxpool]
|
40 |
+
size=2
|
41 |
+
stride=2
|
42 |
+
|
43 |
+
# Residual Block
|
44 |
+
[convolutional]
|
45 |
+
batch_normalize=1
|
46 |
+
filters=64
|
47 |
+
size=3
|
48 |
+
stride=1
|
49 |
+
pad=1
|
50 |
+
activation=leaky
|
51 |
+
|
52 |
+
[convolutional]
|
53 |
+
batch_normalize=1
|
54 |
+
filters=64
|
55 |
+
size=3
|
56 |
+
stride=1
|
57 |
+
pad=1
|
58 |
+
activation=linear
|
59 |
+
|
60 |
+
[shortcut]
|
61 |
+
activation=leaky
|
62 |
+
from=-3
|
63 |
+
|
64 |
+
# Residual Block
|
65 |
+
[convolutional]
|
66 |
+
batch_normalize=1
|
67 |
+
filters=64
|
68 |
+
size=3
|
69 |
+
stride=1
|
70 |
+
pad=1
|
71 |
+
activation=leaky
|
72 |
+
|
73 |
+
[convolutional]
|
74 |
+
batch_normalize=1
|
75 |
+
filters=64
|
76 |
+
size=3
|
77 |
+
stride=1
|
78 |
+
pad=1
|
79 |
+
activation=linear
|
80 |
+
|
81 |
+
[shortcut]
|
82 |
+
activation=leaky
|
83 |
+
from=-3
|
84 |
+
|
85 |
+
# Residual Block
|
86 |
+
[convolutional]
|
87 |
+
batch_normalize=1
|
88 |
+
filters=64
|
89 |
+
size=3
|
90 |
+
stride=1
|
91 |
+
pad=1
|
92 |
+
activation=leaky
|
93 |
+
|
94 |
+
[convolutional]
|
95 |
+
batch_normalize=1
|
96 |
+
filters=64
|
97 |
+
size=3
|
98 |
+
stride=1
|
99 |
+
pad=1
|
100 |
+
activation=linear
|
101 |
+
|
102 |
+
[shortcut]
|
103 |
+
activation=leaky
|
104 |
+
from=-3
|
105 |
+
|
106 |
+
# Strided Residual Block
|
107 |
+
[convolutional]
|
108 |
+
batch_normalize=1
|
109 |
+
filters=128
|
110 |
+
size=3
|
111 |
+
stride=2
|
112 |
+
pad=1
|
113 |
+
activation=leaky
|
114 |
+
|
115 |
+
[convolutional]
|
116 |
+
batch_normalize=1
|
117 |
+
filters=128
|
118 |
+
size=3
|
119 |
+
stride=1
|
120 |
+
pad=1
|
121 |
+
activation=linear
|
122 |
+
|
123 |
+
[shortcut]
|
124 |
+
activation=leaky
|
125 |
+
from=-3
|
126 |
+
|
127 |
+
# Residual Block
|
128 |
+
[convolutional]
|
129 |
+
batch_normalize=1
|
130 |
+
filters=128
|
131 |
+
size=3
|
132 |
+
stride=1
|
133 |
+
pad=1
|
134 |
+
activation=leaky
|
135 |
+
|
136 |
+
[convolutional]
|
137 |
+
batch_normalize=1
|
138 |
+
filters=128
|
139 |
+
size=3
|
140 |
+
stride=1
|
141 |
+
pad=1
|
142 |
+
activation=linear
|
143 |
+
|
144 |
+
[shortcut]
|
145 |
+
activation=leaky
|
146 |
+
from=-3
|
147 |
+
|
148 |
+
# Residual Block
|
149 |
+
[convolutional]
|
150 |
+
batch_normalize=1
|
151 |
+
filters=128
|
152 |
+
size=3
|
153 |
+
stride=1
|
154 |
+
pad=1
|
155 |
+
activation=leaky
|
156 |
+
|
157 |
+
[convolutional]
|
158 |
+
batch_normalize=1
|
159 |
+
filters=128
|
160 |
+
size=3
|
161 |
+
stride=1
|
162 |
+
pad=1
|
163 |
+
activation=linear
|
164 |
+
|
165 |
+
[shortcut]
|
166 |
+
activation=leaky
|
167 |
+
from=-3
|
168 |
+
|
169 |
+
# Residual Block
|
170 |
+
[convolutional]
|
171 |
+
batch_normalize=1
|
172 |
+
filters=128
|
173 |
+
size=3
|
174 |
+
stride=1
|
175 |
+
pad=1
|
176 |
+
activation=leaky
|
177 |
+
|
178 |
+
[convolutional]
|
179 |
+
batch_normalize=1
|
180 |
+
filters=128
|
181 |
+
size=3
|
182 |
+
stride=1
|
183 |
+
pad=1
|
184 |
+
activation=linear
|
185 |
+
|
186 |
+
[shortcut]
|
187 |
+
activation=leaky
|
188 |
+
from=-3
|
189 |
+
|
190 |
+
# Strided Residual Block
|
191 |
+
[convolutional]
|
192 |
+
batch_normalize=1
|
193 |
+
filters=256
|
194 |
+
size=3
|
195 |
+
stride=2
|
196 |
+
pad=1
|
197 |
+
activation=leaky
|
198 |
+
|
199 |
+
[convolutional]
|
200 |
+
batch_normalize=1
|
201 |
+
filters=256
|
202 |
+
size=3
|
203 |
+
stride=1
|
204 |
+
pad=1
|
205 |
+
activation=linear
|
206 |
+
|
207 |
+
[shortcut]
|
208 |
+
activation=leaky
|
209 |
+
from=-3
|
210 |
+
|
211 |
+
# Residual Block
|
212 |
+
[convolutional]
|
213 |
+
batch_normalize=1
|
214 |
+
filters=256
|
215 |
+
size=3
|
216 |
+
stride=1
|
217 |
+
pad=1
|
218 |
+
activation=leaky
|
219 |
+
|
220 |
+
[convolutional]
|
221 |
+
batch_normalize=1
|
222 |
+
filters=256
|
223 |
+
size=3
|
224 |
+
stride=1
|
225 |
+
pad=1
|
226 |
+
activation=linear
|
227 |
+
|
228 |
+
[shortcut]
|
229 |
+
activation=leaky
|
230 |
+
from=-3
|
231 |
+
|
232 |
+
# Residual Block
|
233 |
+
[convolutional]
|
234 |
+
batch_normalize=1
|
235 |
+
filters=256
|
236 |
+
size=3
|
237 |
+
stride=1
|
238 |
+
pad=1
|
239 |
+
activation=leaky
|
240 |
+
|
241 |
+
[convolutional]
|
242 |
+
batch_normalize=1
|
243 |
+
filters=256
|
244 |
+
size=3
|
245 |
+
stride=1
|
246 |
+
pad=1
|
247 |
+
activation=linear
|
248 |
+
|
249 |
+
[shortcut]
|
250 |
+
activation=leaky
|
251 |
+
from=-3
|
252 |
+
|
253 |
+
# Residual Block
|
254 |
+
[convolutional]
|
255 |
+
batch_normalize=1
|
256 |
+
filters=256
|
257 |
+
size=3
|
258 |
+
stride=1
|
259 |
+
pad=1
|
260 |
+
activation=leaky
|
261 |
+
|
262 |
+
[convolutional]
|
263 |
+
batch_normalize=1
|
264 |
+
filters=256
|
265 |
+
size=3
|
266 |
+
stride=1
|
267 |
+
pad=1
|
268 |
+
activation=linear
|
269 |
+
|
270 |
+
[shortcut]
|
271 |
+
activation=leaky
|
272 |
+
from=-3
|
273 |
+
|
274 |
+
# Residual Block
|
275 |
+
[convolutional]
|
276 |
+
batch_normalize=1
|
277 |
+
filters=256
|
278 |
+
size=3
|
279 |
+
stride=1
|
280 |
+
pad=1
|
281 |
+
activation=leaky
|
282 |
+
|
283 |
+
[convolutional]
|
284 |
+
batch_normalize=1
|
285 |
+
filters=256
|
286 |
+
size=3
|
287 |
+
stride=1
|
288 |
+
pad=1
|
289 |
+
activation=linear
|
290 |
+
|
291 |
+
[shortcut]
|
292 |
+
activation=leaky
|
293 |
+
from=-3
|
294 |
+
|
295 |
+
# Residual Block
|
296 |
+
[convolutional]
|
297 |
+
batch_normalize=1
|
298 |
+
filters=256
|
299 |
+
size=3
|
300 |
+
stride=1
|
301 |
+
pad=1
|
302 |
+
activation=leaky
|
303 |
+
|
304 |
+
[convolutional]
|
305 |
+
batch_normalize=1
|
306 |
+
filters=256
|
307 |
+
size=3
|
308 |
+
stride=1
|
309 |
+
pad=1
|
310 |
+
activation=linear
|
311 |
+
|
312 |
+
[shortcut]
|
313 |
+
activation=leaky
|
314 |
+
from=-3
|
315 |
+
|
316 |
+
# Residual Block
|
317 |
+
[convolutional]
|
318 |
+
batch_normalize=1
|
319 |
+
filters=512
|
320 |
+
size=3
|
321 |
+
stride=2
|
322 |
+
pad=1
|
323 |
+
activation=leaky
|
324 |
+
|
325 |
+
[convolutional]
|
326 |
+
batch_normalize=1
|
327 |
+
filters=512
|
328 |
+
size=3
|
329 |
+
stride=1
|
330 |
+
pad=1
|
331 |
+
activation=linear
|
332 |
+
|
333 |
+
[shortcut]
|
334 |
+
activation=leaky
|
335 |
+
from=-3
|
336 |
+
|
337 |
+
# Residual Block
|
338 |
+
[convolutional]
|
339 |
+
batch_normalize=1
|
340 |
+
filters=512
|
341 |
+
size=3
|
342 |
+
stride=1
|
343 |
+
pad=1
|
344 |
+
activation=leaky
|
345 |
+
|
346 |
+
[convolutional]
|
347 |
+
batch_normalize=1
|
348 |
+
filters=512
|
349 |
+
size=3
|
350 |
+
stride=1
|
351 |
+
pad=1
|
352 |
+
activation=linear
|
353 |
+
|
354 |
+
[shortcut]
|
355 |
+
activation=leaky
|
356 |
+
from=-3
|
357 |
+
|
358 |
+
# Residual Block
|
359 |
+
[convolutional]
|
360 |
+
batch_normalize=1
|
361 |
+
filters=512
|
362 |
+
size=3
|
363 |
+
stride=1
|
364 |
+
pad=1
|
365 |
+
activation=leaky
|
366 |
+
|
367 |
+
[convolutional]
|
368 |
+
batch_normalize=1
|
369 |
+
filters=512
|
370 |
+
size=3
|
371 |
+
stride=1
|
372 |
+
pad=1
|
373 |
+
activation=linear
|
374 |
+
|
375 |
+
[shortcut]
|
376 |
+
activation=leaky
|
377 |
+
from=-3
|
378 |
+
|
379 |
+
|
380 |
+
|
381 |
+
[avgpool]
|
382 |
+
|
383 |
+
[convolutional]
|
384 |
+
filters=1000
|
385 |
+
size=1
|
386 |
+
stride=1
|
387 |
+
pad=1
|
388 |
+
activation=linear
|
389 |
+
|
390 |
+
[softmax]
|
391 |
+
groups=1
|
392 |
+
|
model/cfg/resnet50.cfg
ADDED
@@ -0,0 +1,510 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=4
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
channels=3
|
13 |
+
min_crop=128
|
14 |
+
max_crop=448
|
15 |
+
|
16 |
+
burn_in=1000
|
17 |
+
learning_rate=0.1
|
18 |
+
policy=poly
|
19 |
+
power=4
|
20 |
+
max_batches=800000
|
21 |
+
momentum=0.9
|
22 |
+
decay=0.0005
|
23 |
+
|
24 |
+
angle=7
|
25 |
+
hue=.1
|
26 |
+
saturation=.75
|
27 |
+
exposure=.75
|
28 |
+
aspect=.75
|
29 |
+
|
30 |
+
|
31 |
+
[convolutional]
|
32 |
+
batch_normalize=1
|
33 |
+
filters=64
|
34 |
+
size=7
|
35 |
+
stride=2
|
36 |
+
pad=1
|
37 |
+
activation=leaky
|
38 |
+
|
39 |
+
[maxpool]
|
40 |
+
size=2
|
41 |
+
stride=2
|
42 |
+
|
43 |
+
[convolutional]
|
44 |
+
batch_normalize=1
|
45 |
+
filters=64
|
46 |
+
size=1
|
47 |
+
stride=1
|
48 |
+
pad=1
|
49 |
+
activation=leaky
|
50 |
+
|
51 |
+
[convolutional]
|
52 |
+
batch_normalize=1
|
53 |
+
filters=64
|
54 |
+
size=3
|
55 |
+
stride=1
|
56 |
+
pad=1
|
57 |
+
activation=leaky
|
58 |
+
|
59 |
+
[convolutional]
|
60 |
+
batch_normalize=1
|
61 |
+
filters=256
|
62 |
+
size=1
|
63 |
+
stride=1
|
64 |
+
pad=1
|
65 |
+
activation=linear
|
66 |
+
|
67 |
+
[shortcut]
|
68 |
+
from=-4
|
69 |
+
activation=leaky
|
70 |
+
|
71 |
+
[convolutional]
|
72 |
+
batch_normalize=1
|
73 |
+
filters=64
|
74 |
+
size=1
|
75 |
+
stride=1
|
76 |
+
pad=1
|
77 |
+
activation=leaky
|
78 |
+
|
79 |
+
[convolutional]
|
80 |
+
batch_normalize=1
|
81 |
+
filters=64
|
82 |
+
size=3
|
83 |
+
stride=1
|
84 |
+
pad=1
|
85 |
+
activation=leaky
|
86 |
+
|
87 |
+
[convolutional]
|
88 |
+
batch_normalize=1
|
89 |
+
filters=256
|
90 |
+
size=1
|
91 |
+
stride=1
|
92 |
+
pad=1
|
93 |
+
activation=linear
|
94 |
+
|
95 |
+
[shortcut]
|
96 |
+
from=-4
|
97 |
+
activation=leaky
|
98 |
+
|
99 |
+
[convolutional]
|
100 |
+
batch_normalize=1
|
101 |
+
filters=64
|
102 |
+
size=1
|
103 |
+
stride=1
|
104 |
+
pad=1
|
105 |
+
activation=leaky
|
106 |
+
|
107 |
+
[convolutional]
|
108 |
+
batch_normalize=1
|
109 |
+
filters=64
|
110 |
+
size=3
|
111 |
+
stride=1
|
112 |
+
pad=1
|
113 |
+
activation=leaky
|
114 |
+
|
115 |
+
[convolutional]
|
116 |
+
batch_normalize=1
|
117 |
+
filters=256
|
118 |
+
size=1
|
119 |
+
stride=1
|
120 |
+
pad=1
|
121 |
+
activation=linear
|
122 |
+
|
123 |
+
[shortcut]
|
124 |
+
from=-4
|
125 |
+
activation=leaky
|
126 |
+
|
127 |
+
[convolutional]
|
128 |
+
batch_normalize=1
|
129 |
+
filters=128
|
130 |
+
size=1
|
131 |
+
stride=1
|
132 |
+
pad=1
|
133 |
+
activation=leaky
|
134 |
+
|
135 |
+
[convolutional]
|
136 |
+
batch_normalize=1
|
137 |
+
filters=128
|
138 |
+
size=3
|
139 |
+
stride=2
|
140 |
+
pad=1
|
141 |
+
activation=leaky
|
142 |
+
|
143 |
+
[convolutional]
|
144 |
+
batch_normalize=1
|
145 |
+
filters=512
|
146 |
+
size=1
|
147 |
+
stride=1
|
148 |
+
pad=1
|
149 |
+
activation=linear
|
150 |
+
|
151 |
+
[shortcut]
|
152 |
+
from=-4
|
153 |
+
activation=leaky
|
154 |
+
|
155 |
+
[convolutional]
|
156 |
+
batch_normalize=1
|
157 |
+
filters=128
|
158 |
+
size=1
|
159 |
+
stride=1
|
160 |
+
pad=1
|
161 |
+
activation=leaky
|
162 |
+
|
163 |
+
[convolutional]
|
164 |
+
batch_normalize=1
|
165 |
+
filters=128
|
166 |
+
size=3
|
167 |
+
stride=1
|
168 |
+
pad=1
|
169 |
+
activation=leaky
|
170 |
+
|
171 |
+
[convolutional]
|
172 |
+
batch_normalize=1
|
173 |
+
filters=512
|
174 |
+
size=1
|
175 |
+
stride=1
|
176 |
+
pad=1
|
177 |
+
activation=linear
|
178 |
+
|
179 |
+
[shortcut]
|
180 |
+
from=-4
|
181 |
+
activation=leaky
|
182 |
+
|
183 |
+
[convolutional]
|
184 |
+
batch_normalize=1
|
185 |
+
filters=128
|
186 |
+
size=1
|
187 |
+
stride=1
|
188 |
+
pad=1
|
189 |
+
activation=leaky
|
190 |
+
|
191 |
+
[convolutional]
|
192 |
+
batch_normalize=1
|
193 |
+
filters=128
|
194 |
+
size=3
|
195 |
+
stride=1
|
196 |
+
pad=1
|
197 |
+
activation=leaky
|
198 |
+
|
199 |
+
[convolutional]
|
200 |
+
batch_normalize=1
|
201 |
+
filters=512
|
202 |
+
size=1
|
203 |
+
stride=1
|
204 |
+
pad=1
|
205 |
+
activation=linear
|
206 |
+
|
207 |
+
[shortcut]
|
208 |
+
from=-4
|
209 |
+
activation=leaky
|
210 |
+
|
211 |
+
[convolutional]
|
212 |
+
batch_normalize=1
|
213 |
+
filters=128
|
214 |
+
size=1
|
215 |
+
stride=1
|
216 |
+
pad=1
|
217 |
+
activation=leaky
|
218 |
+
|
219 |
+
[convolutional]
|
220 |
+
batch_normalize=1
|
221 |
+
filters=128
|
222 |
+
size=3
|
223 |
+
stride=1
|
224 |
+
pad=1
|
225 |
+
activation=leaky
|
226 |
+
|
227 |
+
[convolutional]
|
228 |
+
batch_normalize=1
|
229 |
+
filters=512
|
230 |
+
size=1
|
231 |
+
stride=1
|
232 |
+
pad=1
|
233 |
+
activation=linear
|
234 |
+
|
235 |
+
[shortcut]
|
236 |
+
from=-4
|
237 |
+
activation=leaky
|
238 |
+
|
239 |
+
|
240 |
+
# Conv 4
|
241 |
+
[convolutional]
|
242 |
+
batch_normalize=1
|
243 |
+
filters=256
|
244 |
+
size=1
|
245 |
+
stride=1
|
246 |
+
pad=1
|
247 |
+
activation=leaky
|
248 |
+
|
249 |
+
[convolutional]
|
250 |
+
batch_normalize=1
|
251 |
+
filters=256
|
252 |
+
size=3
|
253 |
+
stride=2
|
254 |
+
pad=1
|
255 |
+
activation=leaky
|
256 |
+
|
257 |
+
[convolutional]
|
258 |
+
batch_normalize=1
|
259 |
+
filters=1024
|
260 |
+
size=1
|
261 |
+
stride=1
|
262 |
+
pad=1
|
263 |
+
activation=linear
|
264 |
+
|
265 |
+
[shortcut]
|
266 |
+
from=-4
|
267 |
+
activation=leaky
|
268 |
+
|
269 |
+
[convolutional]
|
270 |
+
batch_normalize=1
|
271 |
+
filters=256
|
272 |
+
size=1
|
273 |
+
stride=1
|
274 |
+
pad=1
|
275 |
+
activation=leaky
|
276 |
+
|
277 |
+
[convolutional]
|
278 |
+
batch_normalize=1
|
279 |
+
filters=256
|
280 |
+
size=3
|
281 |
+
stride=1
|
282 |
+
pad=1
|
283 |
+
activation=leaky
|
284 |
+
|
285 |
+
[convolutional]
|
286 |
+
batch_normalize=1
|
287 |
+
filters=1024
|
288 |
+
size=1
|
289 |
+
stride=1
|
290 |
+
pad=1
|
291 |
+
activation=linear
|
292 |
+
|
293 |
+
[shortcut]
|
294 |
+
from=-4
|
295 |
+
activation=leaky
|
296 |
+
|
297 |
+
[convolutional]
|
298 |
+
batch_normalize=1
|
299 |
+
filters=256
|
300 |
+
size=1
|
301 |
+
stride=1
|
302 |
+
pad=1
|
303 |
+
activation=leaky
|
304 |
+
|
305 |
+
[convolutional]
|
306 |
+
batch_normalize=1
|
307 |
+
filters=256
|
308 |
+
size=3
|
309 |
+
stride=1
|
310 |
+
pad=1
|
311 |
+
activation=leaky
|
312 |
+
|
313 |
+
[convolutional]
|
314 |
+
batch_normalize=1
|
315 |
+
filters=1024
|
316 |
+
size=1
|
317 |
+
stride=1
|
318 |
+
pad=1
|
319 |
+
activation=linear
|
320 |
+
|
321 |
+
[shortcut]
|
322 |
+
from=-4
|
323 |
+
activation=leaky
|
324 |
+
|
325 |
+
[convolutional]
|
326 |
+
batch_normalize=1
|
327 |
+
filters=256
|
328 |
+
size=1
|
329 |
+
stride=1
|
330 |
+
pad=1
|
331 |
+
activation=leaky
|
332 |
+
|
333 |
+
[convolutional]
|
334 |
+
batch_normalize=1
|
335 |
+
filters=256
|
336 |
+
size=3
|
337 |
+
stride=1
|
338 |
+
pad=1
|
339 |
+
activation=leaky
|
340 |
+
|
341 |
+
[convolutional]
|
342 |
+
batch_normalize=1
|
343 |
+
filters=1024
|
344 |
+
size=1
|
345 |
+
stride=1
|
346 |
+
pad=1
|
347 |
+
activation=linear
|
348 |
+
|
349 |
+
[shortcut]
|
350 |
+
from=-4
|
351 |
+
activation=leaky
|
352 |
+
|
353 |
+
[convolutional]
|
354 |
+
batch_normalize=1
|
355 |
+
filters=256
|
356 |
+
size=1
|
357 |
+
stride=1
|
358 |
+
pad=1
|
359 |
+
activation=leaky
|
360 |
+
|
361 |
+
[convolutional]
|
362 |
+
batch_normalize=1
|
363 |
+
filters=256
|
364 |
+
size=3
|
365 |
+
stride=1
|
366 |
+
pad=1
|
367 |
+
activation=leaky
|
368 |
+
|
369 |
+
[convolutional]
|
370 |
+
batch_normalize=1
|
371 |
+
filters=1024
|
372 |
+
size=1
|
373 |
+
stride=1
|
374 |
+
pad=1
|
375 |
+
activation=linear
|
376 |
+
|
377 |
+
[shortcut]
|
378 |
+
from=-4
|
379 |
+
activation=leaky
|
380 |
+
|
381 |
+
[convolutional]
|
382 |
+
batch_normalize=1
|
383 |
+
filters=256
|
384 |
+
size=1
|
385 |
+
stride=1
|
386 |
+
pad=1
|
387 |
+
activation=leaky
|
388 |
+
|
389 |
+
[convolutional]
|
390 |
+
batch_normalize=1
|
391 |
+
filters=256
|
392 |
+
size=3
|
393 |
+
stride=1
|
394 |
+
pad=1
|
395 |
+
activation=leaky
|
396 |
+
|
397 |
+
[convolutional]
|
398 |
+
batch_normalize=1
|
399 |
+
filters=1024
|
400 |
+
size=1
|
401 |
+
stride=1
|
402 |
+
pad=1
|
403 |
+
activation=linear
|
404 |
+
|
405 |
+
[shortcut]
|
406 |
+
from=-4
|
407 |
+
activation=leaky
|
408 |
+
|
409 |
+
#Conv 5
|
410 |
+
[convolutional]
|
411 |
+
batch_normalize=1
|
412 |
+
filters=512
|
413 |
+
size=1
|
414 |
+
stride=1
|
415 |
+
pad=1
|
416 |
+
activation=leaky
|
417 |
+
|
418 |
+
[convolutional]
|
419 |
+
batch_normalize=1
|
420 |
+
filters=512
|
421 |
+
size=3
|
422 |
+
stride=2
|
423 |
+
pad=1
|
424 |
+
activation=leaky
|
425 |
+
|
426 |
+
[convolutional]
|
427 |
+
batch_normalize=1
|
428 |
+
filters=2048
|
429 |
+
size=1
|
430 |
+
stride=1
|
431 |
+
pad=1
|
432 |
+
activation=linear
|
433 |
+
|
434 |
+
[shortcut]
|
435 |
+
from=-4
|
436 |
+
activation=leaky
|
437 |
+
|
438 |
+
[convolutional]
|
439 |
+
batch_normalize=1
|
440 |
+
filters=512
|
441 |
+
size=1
|
442 |
+
stride=1
|
443 |
+
pad=1
|
444 |
+
activation=leaky
|
445 |
+
|
446 |
+
[convolutional]
|
447 |
+
batch_normalize=1
|
448 |
+
filters=512
|
449 |
+
size=3
|
450 |
+
stride=1
|
451 |
+
pad=1
|
452 |
+
activation=leaky
|
453 |
+
|
454 |
+
[convolutional]
|
455 |
+
batch_normalize=1
|
456 |
+
filters=2048
|
457 |
+
size=1
|
458 |
+
stride=1
|
459 |
+
pad=1
|
460 |
+
activation=linear
|
461 |
+
|
462 |
+
[shortcut]
|
463 |
+
from=-4
|
464 |
+
activation=leaky
|
465 |
+
|
466 |
+
[convolutional]
|
467 |
+
batch_normalize=1
|
468 |
+
filters=512
|
469 |
+
size=1
|
470 |
+
stride=1
|
471 |
+
pad=1
|
472 |
+
activation=leaky
|
473 |
+
|
474 |
+
[convolutional]
|
475 |
+
batch_normalize=1
|
476 |
+
filters=512
|
477 |
+
size=3
|
478 |
+
stride=1
|
479 |
+
pad=1
|
480 |
+
activation=leaky
|
481 |
+
|
482 |
+
[convolutional]
|
483 |
+
batch_normalize=1
|
484 |
+
filters=2048
|
485 |
+
size=1
|
486 |
+
stride=1
|
487 |
+
pad=1
|
488 |
+
activation=linear
|
489 |
+
|
490 |
+
[shortcut]
|
491 |
+
from=-4
|
492 |
+
activation=leaky
|
493 |
+
|
494 |
+
|
495 |
+
|
496 |
+
|
497 |
+
|
498 |
+
[avgpool]
|
499 |
+
|
500 |
+
[convolutional]
|
501 |
+
filters=1000
|
502 |
+
size=1
|
503 |
+
stride=1
|
504 |
+
pad=1
|
505 |
+
activation=linear
|
506 |
+
|
507 |
+
[softmax]
|
508 |
+
groups=1
|
509 |
+
|
510 |
+
|
model/cfg/resnext101-32x4d.cfg
ADDED
@@ -0,0 +1,1053 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=8
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
channels=3
|
13 |
+
min_crop=128
|
14 |
+
max_crop=448
|
15 |
+
|
16 |
+
burn_in=1000
|
17 |
+
learning_rate=0.1
|
18 |
+
policy=poly
|
19 |
+
power=4
|
20 |
+
max_batches=800000
|
21 |
+
momentum=0.9
|
22 |
+
decay=0.0005
|
23 |
+
|
24 |
+
angle=7
|
25 |
+
hue=.1
|
26 |
+
saturation=.75
|
27 |
+
exposure=.75
|
28 |
+
aspect=.75
|
29 |
+
|
30 |
+
|
31 |
+
|
32 |
+
[convolutional]
|
33 |
+
batch_normalize=1
|
34 |
+
filters=64
|
35 |
+
size=7
|
36 |
+
stride=2
|
37 |
+
pad=1
|
38 |
+
activation=leaky
|
39 |
+
|
40 |
+
[maxpool]
|
41 |
+
size=2
|
42 |
+
stride=2
|
43 |
+
|
44 |
+
[convolutional]
|
45 |
+
batch_normalize=1
|
46 |
+
filters=64
|
47 |
+
size=1
|
48 |
+
stride=1
|
49 |
+
pad=1
|
50 |
+
activation=leaky
|
51 |
+
|
52 |
+
[convolutional]
|
53 |
+
groups = 32
|
54 |
+
batch_normalize=1
|
55 |
+
filters=64
|
56 |
+
size=3
|
57 |
+
stride=1
|
58 |
+
pad=1
|
59 |
+
activation=leaky
|
60 |
+
|
61 |
+
[convolutional]
|
62 |
+
batch_normalize=1
|
63 |
+
filters=512
|
64 |
+
size=1
|
65 |
+
stride=1
|
66 |
+
pad=1
|
67 |
+
activation=linear
|
68 |
+
|
69 |
+
[shortcut]
|
70 |
+
from=-4
|
71 |
+
activation=leaky
|
72 |
+
|
73 |
+
|
74 |
+
[convolutional]
|
75 |
+
batch_normalize=1
|
76 |
+
filters=64
|
77 |
+
size=1
|
78 |
+
stride=1
|
79 |
+
pad=1
|
80 |
+
activation=leaky
|
81 |
+
|
82 |
+
[convolutional]
|
83 |
+
groups = 32
|
84 |
+
batch_normalize=1
|
85 |
+
filters=64
|
86 |
+
size=3
|
87 |
+
stride=1
|
88 |
+
pad=1
|
89 |
+
activation=leaky
|
90 |
+
|
91 |
+
[convolutional]
|
92 |
+
batch_normalize=1
|
93 |
+
filters=512
|
94 |
+
size=1
|
95 |
+
stride=1
|
96 |
+
pad=1
|
97 |
+
activation=linear
|
98 |
+
|
99 |
+
[shortcut]
|
100 |
+
from=-4
|
101 |
+
activation=leaky
|
102 |
+
|
103 |
+
|
104 |
+
[convolutional]
|
105 |
+
batch_normalize=1
|
106 |
+
filters=64
|
107 |
+
size=1
|
108 |
+
stride=1
|
109 |
+
pad=1
|
110 |
+
activation=leaky
|
111 |
+
|
112 |
+
[convolutional]
|
113 |
+
groups = 32
|
114 |
+
batch_normalize=1
|
115 |
+
filters=64
|
116 |
+
size=3
|
117 |
+
stride=1
|
118 |
+
pad=1
|
119 |
+
activation=leaky
|
120 |
+
|
121 |
+
[convolutional]
|
122 |
+
batch_normalize=1
|
123 |
+
filters=512
|
124 |
+
size=1
|
125 |
+
stride=1
|
126 |
+
pad=1
|
127 |
+
activation=linear
|
128 |
+
|
129 |
+
[shortcut]
|
130 |
+
from=-4
|
131 |
+
activation=leaky
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
[convolutional]
|
136 |
+
batch_normalize=1
|
137 |
+
filters=128
|
138 |
+
size=1
|
139 |
+
stride=1
|
140 |
+
pad=1
|
141 |
+
activation=leaky
|
142 |
+
|
143 |
+
[convolutional]
|
144 |
+
groups = 32
|
145 |
+
batch_normalize=1
|
146 |
+
filters=128
|
147 |
+
size=3
|
148 |
+
stride=2
|
149 |
+
pad=1
|
150 |
+
activation=leaky
|
151 |
+
|
152 |
+
[convolutional]
|
153 |
+
batch_normalize=1
|
154 |
+
filters=1024
|
155 |
+
size=1
|
156 |
+
stride=1
|
157 |
+
pad=1
|
158 |
+
activation=linear
|
159 |
+
|
160 |
+
[shortcut]
|
161 |
+
from=-4
|
162 |
+
activation=leaky
|
163 |
+
|
164 |
+
|
165 |
+
|
166 |
+
[convolutional]
|
167 |
+
batch_normalize=1
|
168 |
+
filters=128
|
169 |
+
size=1
|
170 |
+
stride=1
|
171 |
+
pad=1
|
172 |
+
activation=leaky
|
173 |
+
|
174 |
+
[convolutional]
|
175 |
+
groups = 32
|
176 |
+
batch_normalize=1
|
177 |
+
filters=128
|
178 |
+
size=3
|
179 |
+
stride=1
|
180 |
+
pad=1
|
181 |
+
activation=leaky
|
182 |
+
|
183 |
+
[convolutional]
|
184 |
+
batch_normalize=1
|
185 |
+
filters=1024
|
186 |
+
size=1
|
187 |
+
stride=1
|
188 |
+
pad=1
|
189 |
+
activation=linear
|
190 |
+
|
191 |
+
[shortcut]
|
192 |
+
from=-4
|
193 |
+
activation=leaky
|
194 |
+
|
195 |
+
|
196 |
+
[convolutional]
|
197 |
+
batch_normalize=1
|
198 |
+
filters=128
|
199 |
+
size=1
|
200 |
+
stride=1
|
201 |
+
pad=1
|
202 |
+
activation=leaky
|
203 |
+
|
204 |
+
[convolutional]
|
205 |
+
groups = 32
|
206 |
+
batch_normalize=1
|
207 |
+
filters=128
|
208 |
+
size=3
|
209 |
+
stride=1
|
210 |
+
pad=1
|
211 |
+
activation=leaky
|
212 |
+
|
213 |
+
[convolutional]
|
214 |
+
batch_normalize=1
|
215 |
+
filters=1024
|
216 |
+
size=1
|
217 |
+
stride=1
|
218 |
+
pad=1
|
219 |
+
activation=linear
|
220 |
+
|
221 |
+
[shortcut]
|
222 |
+
from=-4
|
223 |
+
activation=leaky
|
224 |
+
|
225 |
+
|
226 |
+
[convolutional]
|
227 |
+
batch_normalize=1
|
228 |
+
filters=128
|
229 |
+
size=1
|
230 |
+
stride=1
|
231 |
+
pad=1
|
232 |
+
activation=leaky
|
233 |
+
|
234 |
+
[convolutional]
|
235 |
+
groups = 32
|
236 |
+
batch_normalize=1
|
237 |
+
filters=128
|
238 |
+
size=3
|
239 |
+
stride=1
|
240 |
+
pad=1
|
241 |
+
activation=leaky
|
242 |
+
|
243 |
+
[convolutional]
|
244 |
+
batch_normalize=1
|
245 |
+
filters=1024
|
246 |
+
size=1
|
247 |
+
stride=1
|
248 |
+
pad=1
|
249 |
+
activation=linear
|
250 |
+
|
251 |
+
[shortcut]
|
252 |
+
from=-4
|
253 |
+
activation=leaky
|
254 |
+
|
255 |
+
|
256 |
+
|
257 |
+
[convolutional]
|
258 |
+
batch_normalize=1
|
259 |
+
filters=256
|
260 |
+
size=1
|
261 |
+
stride=1
|
262 |
+
pad=1
|
263 |
+
activation=leaky
|
264 |
+
|
265 |
+
[convolutional]
|
266 |
+
groups = 32
|
267 |
+
batch_normalize=1
|
268 |
+
filters=256
|
269 |
+
size=3
|
270 |
+
stride=2
|
271 |
+
pad=1
|
272 |
+
activation=leaky
|
273 |
+
|
274 |
+
[convolutional]
|
275 |
+
batch_normalize=1
|
276 |
+
filters=2048
|
277 |
+
size=1
|
278 |
+
stride=1
|
279 |
+
pad=1
|
280 |
+
activation=linear
|
281 |
+
|
282 |
+
[shortcut]
|
283 |
+
from=-4
|
284 |
+
activation=leaky
|
285 |
+
|
286 |
+
|
287 |
+
|
288 |
+
[convolutional]
|
289 |
+
batch_normalize=1
|
290 |
+
filters=256
|
291 |
+
size=1
|
292 |
+
stride=1
|
293 |
+
pad=1
|
294 |
+
activation=leaky
|
295 |
+
|
296 |
+
[convolutional]
|
297 |
+
groups = 32
|
298 |
+
batch_normalize=1
|
299 |
+
filters=256
|
300 |
+
size=3
|
301 |
+
stride=1
|
302 |
+
pad=1
|
303 |
+
activation=leaky
|
304 |
+
|
305 |
+
[convolutional]
|
306 |
+
batch_normalize=1
|
307 |
+
filters=2048
|
308 |
+
size=1
|
309 |
+
stride=1
|
310 |
+
pad=1
|
311 |
+
activation=linear
|
312 |
+
|
313 |
+
[shortcut]
|
314 |
+
from=-4
|
315 |
+
activation=leaky
|
316 |
+
|
317 |
+
|
318 |
+
[convolutional]
|
319 |
+
batch_normalize=1
|
320 |
+
filters=256
|
321 |
+
size=1
|
322 |
+
stride=1
|
323 |
+
pad=1
|
324 |
+
activation=leaky
|
325 |
+
|
326 |
+
[convolutional]
|
327 |
+
groups = 32
|
328 |
+
batch_normalize=1
|
329 |
+
filters=256
|
330 |
+
size=3
|
331 |
+
stride=1
|
332 |
+
pad=1
|
333 |
+
activation=leaky
|
334 |
+
|
335 |
+
[convolutional]
|
336 |
+
batch_normalize=1
|
337 |
+
filters=2048
|
338 |
+
size=1
|
339 |
+
stride=1
|
340 |
+
pad=1
|
341 |
+
activation=linear
|
342 |
+
|
343 |
+
[shortcut]
|
344 |
+
from=-4
|
345 |
+
activation=leaky
|
346 |
+
|
347 |
+
|
348 |
+
[convolutional]
|
349 |
+
batch_normalize=1
|
350 |
+
filters=256
|
351 |
+
size=1
|
352 |
+
stride=1
|
353 |
+
pad=1
|
354 |
+
activation=leaky
|
355 |
+
|
356 |
+
[convolutional]
|
357 |
+
groups = 32
|
358 |
+
batch_normalize=1
|
359 |
+
filters=256
|
360 |
+
size=3
|
361 |
+
stride=1
|
362 |
+
pad=1
|
363 |
+
activation=leaky
|
364 |
+
|
365 |
+
[convolutional]
|
366 |
+
batch_normalize=1
|
367 |
+
filters=2048
|
368 |
+
size=1
|
369 |
+
stride=1
|
370 |
+
pad=1
|
371 |
+
activation=linear
|
372 |
+
|
373 |
+
[shortcut]
|
374 |
+
from=-4
|
375 |
+
activation=leaky
|
376 |
+
|
377 |
+
|
378 |
+
[convolutional]
|
379 |
+
batch_normalize=1
|
380 |
+
filters=256
|
381 |
+
size=1
|
382 |
+
stride=1
|
383 |
+
pad=1
|
384 |
+
activation=leaky
|
385 |
+
|
386 |
+
[convolutional]
|
387 |
+
groups = 32
|
388 |
+
batch_normalize=1
|
389 |
+
filters=256
|
390 |
+
size=3
|
391 |
+
stride=1
|
392 |
+
pad=1
|
393 |
+
activation=leaky
|
394 |
+
|
395 |
+
[convolutional]
|
396 |
+
batch_normalize=1
|
397 |
+
filters=2048
|
398 |
+
size=1
|
399 |
+
stride=1
|
400 |
+
pad=1
|
401 |
+
activation=linear
|
402 |
+
|
403 |
+
[shortcut]
|
404 |
+
from=-4
|
405 |
+
activation=leaky
|
406 |
+
|
407 |
+
|
408 |
+
[convolutional]
|
409 |
+
batch_normalize=1
|
410 |
+
filters=256
|
411 |
+
size=1
|
412 |
+
stride=1
|
413 |
+
pad=1
|
414 |
+
activation=leaky
|
415 |
+
|
416 |
+
[convolutional]
|
417 |
+
groups = 32
|
418 |
+
batch_normalize=1
|
419 |
+
filters=256
|
420 |
+
size=3
|
421 |
+
stride=1
|
422 |
+
pad=1
|
423 |
+
activation=leaky
|
424 |
+
|
425 |
+
[convolutional]
|
426 |
+
batch_normalize=1
|
427 |
+
filters=2048
|
428 |
+
size=1
|
429 |
+
stride=1
|
430 |
+
pad=1
|
431 |
+
activation=linear
|
432 |
+
|
433 |
+
[shortcut]
|
434 |
+
from=-4
|
435 |
+
activation=leaky
|
436 |
+
|
437 |
+
|
438 |
+
[convolutional]
|
439 |
+
batch_normalize=1
|
440 |
+
filters=256
|
441 |
+
size=1
|
442 |
+
stride=1
|
443 |
+
pad=1
|
444 |
+
activation=leaky
|
445 |
+
|
446 |
+
[convolutional]
|
447 |
+
groups = 32
|
448 |
+
batch_normalize=1
|
449 |
+
filters=256
|
450 |
+
size=3
|
451 |
+
stride=1
|
452 |
+
pad=1
|
453 |
+
activation=leaky
|
454 |
+
|
455 |
+
[convolutional]
|
456 |
+
batch_normalize=1
|
457 |
+
filters=2048
|
458 |
+
size=1
|
459 |
+
stride=1
|
460 |
+
pad=1
|
461 |
+
activation=linear
|
462 |
+
|
463 |
+
[shortcut]
|
464 |
+
from=-4
|
465 |
+
activation=leaky
|
466 |
+
|
467 |
+
|
468 |
+
[convolutional]
|
469 |
+
batch_normalize=1
|
470 |
+
filters=256
|
471 |
+
size=1
|
472 |
+
stride=1
|
473 |
+
pad=1
|
474 |
+
activation=leaky
|
475 |
+
|
476 |
+
[convolutional]
|
477 |
+
groups = 32
|
478 |
+
batch_normalize=1
|
479 |
+
filters=256
|
480 |
+
size=3
|
481 |
+
stride=1
|
482 |
+
pad=1
|
483 |
+
activation=leaky
|
484 |
+
|
485 |
+
[convolutional]
|
486 |
+
batch_normalize=1
|
487 |
+
filters=2048
|
488 |
+
size=1
|
489 |
+
stride=1
|
490 |
+
pad=1
|
491 |
+
activation=linear
|
492 |
+
|
493 |
+
[shortcut]
|
494 |
+
from=-4
|
495 |
+
activation=leaky
|
496 |
+
|
497 |
+
|
498 |
+
[convolutional]
|
499 |
+
batch_normalize=1
|
500 |
+
filters=256
|
501 |
+
size=1
|
502 |
+
stride=1
|
503 |
+
pad=1
|
504 |
+
activation=leaky
|
505 |
+
|
506 |
+
[convolutional]
|
507 |
+
groups = 32
|
508 |
+
batch_normalize=1
|
509 |
+
filters=256
|
510 |
+
size=3
|
511 |
+
stride=1
|
512 |
+
pad=1
|
513 |
+
activation=leaky
|
514 |
+
|
515 |
+
[convolutional]
|
516 |
+
batch_normalize=1
|
517 |
+
filters=2048
|
518 |
+
size=1
|
519 |
+
stride=1
|
520 |
+
pad=1
|
521 |
+
activation=linear
|
522 |
+
|
523 |
+
[shortcut]
|
524 |
+
from=-4
|
525 |
+
activation=leaky
|
526 |
+
|
527 |
+
|
528 |
+
[convolutional]
|
529 |
+
batch_normalize=1
|
530 |
+
filters=256
|
531 |
+
size=1
|
532 |
+
stride=1
|
533 |
+
pad=1
|
534 |
+
activation=leaky
|
535 |
+
|
536 |
+
[convolutional]
|
537 |
+
groups = 32
|
538 |
+
batch_normalize=1
|
539 |
+
filters=256
|
540 |
+
size=3
|
541 |
+
stride=1
|
542 |
+
pad=1
|
543 |
+
activation=leaky
|
544 |
+
|
545 |
+
[convolutional]
|
546 |
+
batch_normalize=1
|
547 |
+
filters=2048
|
548 |
+
size=1
|
549 |
+
stride=1
|
550 |
+
pad=1
|
551 |
+
activation=linear
|
552 |
+
|
553 |
+
[shortcut]
|
554 |
+
from=-4
|
555 |
+
activation=leaky
|
556 |
+
|
557 |
+
|
558 |
+
[convolutional]
|
559 |
+
batch_normalize=1
|
560 |
+
filters=256
|
561 |
+
size=1
|
562 |
+
stride=1
|
563 |
+
pad=1
|
564 |
+
activation=leaky
|
565 |
+
|
566 |
+
[convolutional]
|
567 |
+
groups = 32
|
568 |
+
batch_normalize=1
|
569 |
+
filters=256
|
570 |
+
size=3
|
571 |
+
stride=1
|
572 |
+
pad=1
|
573 |
+
activation=leaky
|
574 |
+
|
575 |
+
[convolutional]
|
576 |
+
batch_normalize=1
|
577 |
+
filters=2048
|
578 |
+
size=1
|
579 |
+
stride=1
|
580 |
+
pad=1
|
581 |
+
activation=linear
|
582 |
+
|
583 |
+
[shortcut]
|
584 |
+
from=-4
|
585 |
+
activation=leaky
|
586 |
+
|
587 |
+
|
588 |
+
[convolutional]
|
589 |
+
batch_normalize=1
|
590 |
+
filters=256
|
591 |
+
size=1
|
592 |
+
stride=1
|
593 |
+
pad=1
|
594 |
+
activation=leaky
|
595 |
+
|
596 |
+
[convolutional]
|
597 |
+
groups = 32
|
598 |
+
batch_normalize=1
|
599 |
+
filters=256
|
600 |
+
size=3
|
601 |
+
stride=1
|
602 |
+
pad=1
|
603 |
+
activation=leaky
|
604 |
+
|
605 |
+
[convolutional]
|
606 |
+
batch_normalize=1
|
607 |
+
filters=2048
|
608 |
+
size=1
|
609 |
+
stride=1
|
610 |
+
pad=1
|
611 |
+
activation=linear
|
612 |
+
|
613 |
+
[shortcut]
|
614 |
+
from=-4
|
615 |
+
activation=leaky
|
616 |
+
|
617 |
+
|
618 |
+
[convolutional]
|
619 |
+
batch_normalize=1
|
620 |
+
filters=256
|
621 |
+
size=1
|
622 |
+
stride=1
|
623 |
+
pad=1
|
624 |
+
activation=leaky
|
625 |
+
|
626 |
+
[convolutional]
|
627 |
+
groups = 32
|
628 |
+
batch_normalize=1
|
629 |
+
filters=256
|
630 |
+
size=3
|
631 |
+
stride=1
|
632 |
+
pad=1
|
633 |
+
activation=leaky
|
634 |
+
|
635 |
+
[convolutional]
|
636 |
+
batch_normalize=1
|
637 |
+
filters=2048
|
638 |
+
size=1
|
639 |
+
stride=1
|
640 |
+
pad=1
|
641 |
+
activation=linear
|
642 |
+
|
643 |
+
[shortcut]
|
644 |
+
from=-4
|
645 |
+
activation=leaky
|
646 |
+
|
647 |
+
|
648 |
+
[convolutional]
|
649 |
+
batch_normalize=1
|
650 |
+
filters=256
|
651 |
+
size=1
|
652 |
+
stride=1
|
653 |
+
pad=1
|
654 |
+
activation=leaky
|
655 |
+
|
656 |
+
[convolutional]
|
657 |
+
groups = 32
|
658 |
+
batch_normalize=1
|
659 |
+
filters=256
|
660 |
+
size=3
|
661 |
+
stride=1
|
662 |
+
pad=1
|
663 |
+
activation=leaky
|
664 |
+
|
665 |
+
[convolutional]
|
666 |
+
batch_normalize=1
|
667 |
+
filters=2048
|
668 |
+
size=1
|
669 |
+
stride=1
|
670 |
+
pad=1
|
671 |
+
activation=linear
|
672 |
+
|
673 |
+
[shortcut]
|
674 |
+
from=-4
|
675 |
+
activation=leaky
|
676 |
+
|
677 |
+
|
678 |
+
[convolutional]
|
679 |
+
batch_normalize=1
|
680 |
+
filters=256
|
681 |
+
size=1
|
682 |
+
stride=1
|
683 |
+
pad=1
|
684 |
+
activation=leaky
|
685 |
+
|
686 |
+
[convolutional]
|
687 |
+
groups = 32
|
688 |
+
batch_normalize=1
|
689 |
+
filters=256
|
690 |
+
size=3
|
691 |
+
stride=1
|
692 |
+
pad=1
|
693 |
+
activation=leaky
|
694 |
+
|
695 |
+
[convolutional]
|
696 |
+
batch_normalize=1
|
697 |
+
filters=2048
|
698 |
+
size=1
|
699 |
+
stride=1
|
700 |
+
pad=1
|
701 |
+
activation=linear
|
702 |
+
|
703 |
+
[shortcut]
|
704 |
+
from=-4
|
705 |
+
activation=leaky
|
706 |
+
|
707 |
+
|
708 |
+
[convolutional]
|
709 |
+
batch_normalize=1
|
710 |
+
filters=256
|
711 |
+
size=1
|
712 |
+
stride=1
|
713 |
+
pad=1
|
714 |
+
activation=leaky
|
715 |
+
|
716 |
+
[convolutional]
|
717 |
+
groups = 32
|
718 |
+
batch_normalize=1
|
719 |
+
filters=256
|
720 |
+
size=3
|
721 |
+
stride=1
|
722 |
+
pad=1
|
723 |
+
activation=leaky
|
724 |
+
|
725 |
+
[convolutional]
|
726 |
+
batch_normalize=1
|
727 |
+
filters=2048
|
728 |
+
size=1
|
729 |
+
stride=1
|
730 |
+
pad=1
|
731 |
+
activation=linear
|
732 |
+
|
733 |
+
[shortcut]
|
734 |
+
from=-4
|
735 |
+
activation=leaky
|
736 |
+
|
737 |
+
|
738 |
+
[convolutional]
|
739 |
+
batch_normalize=1
|
740 |
+
filters=256
|
741 |
+
size=1
|
742 |
+
stride=1
|
743 |
+
pad=1
|
744 |
+
activation=leaky
|
745 |
+
|
746 |
+
[convolutional]
|
747 |
+
groups = 32
|
748 |
+
batch_normalize=1
|
749 |
+
filters=256
|
750 |
+
size=3
|
751 |
+
stride=1
|
752 |
+
pad=1
|
753 |
+
activation=leaky
|
754 |
+
|
755 |
+
[convolutional]
|
756 |
+
batch_normalize=1
|
757 |
+
filters=2048
|
758 |
+
size=1
|
759 |
+
stride=1
|
760 |
+
pad=1
|
761 |
+
activation=linear
|
762 |
+
|
763 |
+
[shortcut]
|
764 |
+
from=-4
|
765 |
+
activation=leaky
|
766 |
+
|
767 |
+
|
768 |
+
[convolutional]
|
769 |
+
batch_normalize=1
|
770 |
+
filters=256
|
771 |
+
size=1
|
772 |
+
stride=1
|
773 |
+
pad=1
|
774 |
+
activation=leaky
|
775 |
+
|
776 |
+
[convolutional]
|
777 |
+
groups = 32
|
778 |
+
batch_normalize=1
|
779 |
+
filters=256
|
780 |
+
size=3
|
781 |
+
stride=1
|
782 |
+
pad=1
|
783 |
+
activation=leaky
|
784 |
+
|
785 |
+
[convolutional]
|
786 |
+
batch_normalize=1
|
787 |
+
filters=2048
|
788 |
+
size=1
|
789 |
+
stride=1
|
790 |
+
pad=1
|
791 |
+
activation=linear
|
792 |
+
|
793 |
+
[shortcut]
|
794 |
+
from=-4
|
795 |
+
activation=leaky
|
796 |
+
|
797 |
+
|
798 |
+
[convolutional]
|
799 |
+
batch_normalize=1
|
800 |
+
filters=256
|
801 |
+
size=1
|
802 |
+
stride=1
|
803 |
+
pad=1
|
804 |
+
activation=leaky
|
805 |
+
|
806 |
+
[convolutional]
|
807 |
+
groups = 32
|
808 |
+
batch_normalize=1
|
809 |
+
filters=256
|
810 |
+
size=3
|
811 |
+
stride=1
|
812 |
+
pad=1
|
813 |
+
activation=leaky
|
814 |
+
|
815 |
+
[convolutional]
|
816 |
+
batch_normalize=1
|
817 |
+
filters=2048
|
818 |
+
size=1
|
819 |
+
stride=1
|
820 |
+
pad=1
|
821 |
+
activation=linear
|
822 |
+
|
823 |
+
[shortcut]
|
824 |
+
from=-4
|
825 |
+
activation=leaky
|
826 |
+
|
827 |
+
|
828 |
+
[convolutional]
|
829 |
+
batch_normalize=1
|
830 |
+
filters=256
|
831 |
+
size=1
|
832 |
+
stride=1
|
833 |
+
pad=1
|
834 |
+
activation=leaky
|
835 |
+
|
836 |
+
[convolutional]
|
837 |
+
groups = 32
|
838 |
+
batch_normalize=1
|
839 |
+
filters=256
|
840 |
+
size=3
|
841 |
+
stride=1
|
842 |
+
pad=1
|
843 |
+
activation=leaky
|
844 |
+
|
845 |
+
[convolutional]
|
846 |
+
batch_normalize=1
|
847 |
+
filters=2048
|
848 |
+
size=1
|
849 |
+
stride=1
|
850 |
+
pad=1
|
851 |
+
activation=linear
|
852 |
+
|
853 |
+
[shortcut]
|
854 |
+
from=-4
|
855 |
+
activation=leaky
|
856 |
+
|
857 |
+
|
858 |
+
[convolutional]
|
859 |
+
batch_normalize=1
|
860 |
+
filters=256
|
861 |
+
size=1
|
862 |
+
stride=1
|
863 |
+
pad=1
|
864 |
+
activation=leaky
|
865 |
+
|
866 |
+
[convolutional]
|
867 |
+
groups = 32
|
868 |
+
batch_normalize=1
|
869 |
+
filters=256
|
870 |
+
size=3
|
871 |
+
stride=1
|
872 |
+
pad=1
|
873 |
+
activation=leaky
|
874 |
+
|
875 |
+
[convolutional]
|
876 |
+
batch_normalize=1
|
877 |
+
filters=2048
|
878 |
+
size=1
|
879 |
+
stride=1
|
880 |
+
pad=1
|
881 |
+
activation=linear
|
882 |
+
|
883 |
+
[shortcut]
|
884 |
+
from=-4
|
885 |
+
activation=leaky
|
886 |
+
|
887 |
+
|
888 |
+
[convolutional]
|
889 |
+
batch_normalize=1
|
890 |
+
filters=256
|
891 |
+
size=1
|
892 |
+
stride=1
|
893 |
+
pad=1
|
894 |
+
activation=leaky
|
895 |
+
|
896 |
+
[convolutional]
|
897 |
+
groups = 32
|
898 |
+
batch_normalize=1
|
899 |
+
filters=256
|
900 |
+
size=3
|
901 |
+
stride=1
|
902 |
+
pad=1
|
903 |
+
activation=leaky
|
904 |
+
|
905 |
+
[convolutional]
|
906 |
+
batch_normalize=1
|
907 |
+
filters=2048
|
908 |
+
size=1
|
909 |
+
stride=1
|
910 |
+
pad=1
|
911 |
+
activation=linear
|
912 |
+
|
913 |
+
[shortcut]
|
914 |
+
from=-4
|
915 |
+
activation=leaky
|
916 |
+
|
917 |
+
|
918 |
+
[convolutional]
|
919 |
+
batch_normalize=1
|
920 |
+
filters=256
|
921 |
+
size=1
|
922 |
+
stride=1
|
923 |
+
pad=1
|
924 |
+
activation=leaky
|
925 |
+
|
926 |
+
[convolutional]
|
927 |
+
groups = 32
|
928 |
+
batch_normalize=1
|
929 |
+
filters=256
|
930 |
+
size=3
|
931 |
+
stride=1
|
932 |
+
pad=1
|
933 |
+
activation=leaky
|
934 |
+
|
935 |
+
[convolutional]
|
936 |
+
batch_normalize=1
|
937 |
+
filters=2048
|
938 |
+
size=1
|
939 |
+
stride=1
|
940 |
+
pad=1
|
941 |
+
activation=linear
|
942 |
+
|
943 |
+
[shortcut]
|
944 |
+
from=-4
|
945 |
+
activation=leaky
|
946 |
+
|
947 |
+
|
948 |
+
|
949 |
+
[convolutional]
|
950 |
+
batch_normalize=1
|
951 |
+
filters=512
|
952 |
+
size=1
|
953 |
+
stride=1
|
954 |
+
pad=1
|
955 |
+
activation=leaky
|
956 |
+
|
957 |
+
[convolutional]
|
958 |
+
groups = 32
|
959 |
+
batch_normalize=1
|
960 |
+
filters=512
|
961 |
+
size=3
|
962 |
+
stride=2
|
963 |
+
pad=1
|
964 |
+
activation=leaky
|
965 |
+
|
966 |
+
[convolutional]
|
967 |
+
batch_normalize=1
|
968 |
+
filters=4096
|
969 |
+
size=1
|
970 |
+
stride=1
|
971 |
+
pad=1
|
972 |
+
activation=linear
|
973 |
+
|
974 |
+
[shortcut]
|
975 |
+
from=-4
|
976 |
+
activation=leaky
|
977 |
+
|
978 |
+
|
979 |
+
|
980 |
+
[convolutional]
|
981 |
+
batch_normalize=1
|
982 |
+
filters=512
|
983 |
+
size=1
|
984 |
+
stride=1
|
985 |
+
pad=1
|
986 |
+
activation=leaky
|
987 |
+
|
988 |
+
[convolutional]
|
989 |
+
groups = 32
|
990 |
+
batch_normalize=1
|
991 |
+
filters=512
|
992 |
+
size=3
|
993 |
+
stride=1
|
994 |
+
pad=1
|
995 |
+
activation=leaky
|
996 |
+
|
997 |
+
[convolutional]
|
998 |
+
batch_normalize=1
|
999 |
+
filters=4096
|
1000 |
+
size=1
|
1001 |
+
stride=1
|
1002 |
+
pad=1
|
1003 |
+
activation=linear
|
1004 |
+
|
1005 |
+
[shortcut]
|
1006 |
+
from=-4
|
1007 |
+
activation=leaky
|
1008 |
+
|
1009 |
+
|
1010 |
+
[convolutional]
|
1011 |
+
batch_normalize=1
|
1012 |
+
filters=512
|
1013 |
+
size=1
|
1014 |
+
stride=1
|
1015 |
+
pad=1
|
1016 |
+
activation=leaky
|
1017 |
+
|
1018 |
+
[convolutional]
|
1019 |
+
groups = 32
|
1020 |
+
batch_normalize=1
|
1021 |
+
filters=512
|
1022 |
+
size=3
|
1023 |
+
stride=1
|
1024 |
+
pad=1
|
1025 |
+
activation=leaky
|
1026 |
+
|
1027 |
+
[convolutional]
|
1028 |
+
batch_normalize=1
|
1029 |
+
filters=4096
|
1030 |
+
size=1
|
1031 |
+
stride=1
|
1032 |
+
pad=1
|
1033 |
+
activation=linear
|
1034 |
+
|
1035 |
+
[shortcut]
|
1036 |
+
from=-4
|
1037 |
+
activation=leaky
|
1038 |
+
|
1039 |
+
|
1040 |
+
|
1041 |
+
|
1042 |
+
[avgpool]
|
1043 |
+
|
1044 |
+
[convolutional]
|
1045 |
+
filters=1000
|
1046 |
+
size=1
|
1047 |
+
stride=1
|
1048 |
+
pad=1
|
1049 |
+
activation=linear
|
1050 |
+
|
1051 |
+
[softmax]
|
1052 |
+
groups=1
|
1053 |
+
|
model/cfg/resnext152-32x4d.cfg
ADDED
@@ -0,0 +1,1562 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=16
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
channels=3
|
13 |
+
min_crop=128
|
14 |
+
max_crop=448
|
15 |
+
|
16 |
+
burn_in=1000
|
17 |
+
learning_rate=0.1
|
18 |
+
policy=poly
|
19 |
+
power=4
|
20 |
+
max_batches=800000
|
21 |
+
momentum=0.9
|
22 |
+
decay=0.0005
|
23 |
+
|
24 |
+
angle=7
|
25 |
+
hue=.1
|
26 |
+
saturation=.75
|
27 |
+
exposure=.75
|
28 |
+
aspect=.75
|
29 |
+
|
30 |
+
|
31 |
+
[convolutional]
|
32 |
+
batch_normalize=1
|
33 |
+
filters=64
|
34 |
+
size=7
|
35 |
+
stride=2
|
36 |
+
pad=1
|
37 |
+
activation=leaky
|
38 |
+
|
39 |
+
[maxpool]
|
40 |
+
size=2
|
41 |
+
stride=2
|
42 |
+
|
43 |
+
[convolutional]
|
44 |
+
batch_normalize=1
|
45 |
+
filters=64
|
46 |
+
size=1
|
47 |
+
stride=1
|
48 |
+
pad=1
|
49 |
+
activation=leaky
|
50 |
+
|
51 |
+
[convolutional]
|
52 |
+
groups = 32
|
53 |
+
batch_normalize=1
|
54 |
+
filters=64
|
55 |
+
size=3
|
56 |
+
stride=1
|
57 |
+
pad=1
|
58 |
+
activation=leaky
|
59 |
+
|
60 |
+
[convolutional]
|
61 |
+
batch_normalize=1
|
62 |
+
filters=512
|
63 |
+
size=1
|
64 |
+
stride=1
|
65 |
+
pad=1
|
66 |
+
activation=linear
|
67 |
+
|
68 |
+
[shortcut]
|
69 |
+
from=-4
|
70 |
+
activation=leaky
|
71 |
+
|
72 |
+
|
73 |
+
[convolutional]
|
74 |
+
batch_normalize=1
|
75 |
+
filters=64
|
76 |
+
size=1
|
77 |
+
stride=1
|
78 |
+
pad=1
|
79 |
+
activation=leaky
|
80 |
+
|
81 |
+
[convolutional]
|
82 |
+
groups = 32
|
83 |
+
batch_normalize=1
|
84 |
+
filters=64
|
85 |
+
size=3
|
86 |
+
stride=1
|
87 |
+
pad=1
|
88 |
+
activation=leaky
|
89 |
+
|
90 |
+
[convolutional]
|
91 |
+
batch_normalize=1
|
92 |
+
filters=512
|
93 |
+
size=1
|
94 |
+
stride=1
|
95 |
+
pad=1
|
96 |
+
activation=linear
|
97 |
+
|
98 |
+
[shortcut]
|
99 |
+
from=-4
|
100 |
+
activation=leaky
|
101 |
+
|
102 |
+
|
103 |
+
[convolutional]
|
104 |
+
batch_normalize=1
|
105 |
+
filters=64
|
106 |
+
size=1
|
107 |
+
stride=1
|
108 |
+
pad=1
|
109 |
+
activation=leaky
|
110 |
+
|
111 |
+
[convolutional]
|
112 |
+
groups = 32
|
113 |
+
batch_normalize=1
|
114 |
+
filters=64
|
115 |
+
size=3
|
116 |
+
stride=1
|
117 |
+
pad=1
|
118 |
+
activation=leaky
|
119 |
+
|
120 |
+
[convolutional]
|
121 |
+
batch_normalize=1
|
122 |
+
filters=512
|
123 |
+
size=1
|
124 |
+
stride=1
|
125 |
+
pad=1
|
126 |
+
activation=linear
|
127 |
+
|
128 |
+
[shortcut]
|
129 |
+
from=-4
|
130 |
+
activation=leaky
|
131 |
+
|
132 |
+
|
133 |
+
|
134 |
+
[convolutional]
|
135 |
+
batch_normalize=1
|
136 |
+
filters=128
|
137 |
+
size=1
|
138 |
+
stride=1
|
139 |
+
pad=1
|
140 |
+
activation=leaky
|
141 |
+
|
142 |
+
[convolutional]
|
143 |
+
groups = 32
|
144 |
+
batch_normalize=1
|
145 |
+
filters=128
|
146 |
+
size=3
|
147 |
+
stride=2
|
148 |
+
pad=1
|
149 |
+
activation=leaky
|
150 |
+
|
151 |
+
[convolutional]
|
152 |
+
batch_normalize=1
|
153 |
+
filters=1024
|
154 |
+
size=1
|
155 |
+
stride=1
|
156 |
+
pad=1
|
157 |
+
activation=linear
|
158 |
+
|
159 |
+
[shortcut]
|
160 |
+
from=-4
|
161 |
+
activation=leaky
|
162 |
+
|
163 |
+
|
164 |
+
|
165 |
+
[convolutional]
|
166 |
+
batch_normalize=1
|
167 |
+
filters=128
|
168 |
+
size=1
|
169 |
+
stride=1
|
170 |
+
pad=1
|
171 |
+
activation=leaky
|
172 |
+
|
173 |
+
[convolutional]
|
174 |
+
groups = 32
|
175 |
+
batch_normalize=1
|
176 |
+
filters=128
|
177 |
+
size=3
|
178 |
+
stride=1
|
179 |
+
pad=1
|
180 |
+
activation=leaky
|
181 |
+
|
182 |
+
[convolutional]
|
183 |
+
batch_normalize=1
|
184 |
+
filters=1024
|
185 |
+
size=1
|
186 |
+
stride=1
|
187 |
+
pad=1
|
188 |
+
activation=linear
|
189 |
+
|
190 |
+
[shortcut]
|
191 |
+
from=-4
|
192 |
+
activation=leaky
|
193 |
+
|
194 |
+
|
195 |
+
[convolutional]
|
196 |
+
batch_normalize=1
|
197 |
+
filters=128
|
198 |
+
size=1
|
199 |
+
stride=1
|
200 |
+
pad=1
|
201 |
+
activation=leaky
|
202 |
+
|
203 |
+
[convolutional]
|
204 |
+
groups = 32
|
205 |
+
batch_normalize=1
|
206 |
+
filters=128
|
207 |
+
size=3
|
208 |
+
stride=1
|
209 |
+
pad=1
|
210 |
+
activation=leaky
|
211 |
+
|
212 |
+
[convolutional]
|
213 |
+
batch_normalize=1
|
214 |
+
filters=1024
|
215 |
+
size=1
|
216 |
+
stride=1
|
217 |
+
pad=1
|
218 |
+
activation=linear
|
219 |
+
|
220 |
+
[shortcut]
|
221 |
+
from=-4
|
222 |
+
activation=leaky
|
223 |
+
|
224 |
+
|
225 |
+
[convolutional]
|
226 |
+
batch_normalize=1
|
227 |
+
filters=128
|
228 |
+
size=1
|
229 |
+
stride=1
|
230 |
+
pad=1
|
231 |
+
activation=leaky
|
232 |
+
|
233 |
+
[convolutional]
|
234 |
+
groups = 32
|
235 |
+
batch_normalize=1
|
236 |
+
filters=128
|
237 |
+
size=3
|
238 |
+
stride=1
|
239 |
+
pad=1
|
240 |
+
activation=leaky
|
241 |
+
|
242 |
+
[convolutional]
|
243 |
+
batch_normalize=1
|
244 |
+
filters=1024
|
245 |
+
size=1
|
246 |
+
stride=1
|
247 |
+
pad=1
|
248 |
+
activation=linear
|
249 |
+
|
250 |
+
[shortcut]
|
251 |
+
from=-4
|
252 |
+
activation=leaky
|
253 |
+
|
254 |
+
|
255 |
+
[convolutional]
|
256 |
+
batch_normalize=1
|
257 |
+
filters=128
|
258 |
+
size=1
|
259 |
+
stride=1
|
260 |
+
pad=1
|
261 |
+
activation=leaky
|
262 |
+
|
263 |
+
[convolutional]
|
264 |
+
groups = 32
|
265 |
+
batch_normalize=1
|
266 |
+
filters=128
|
267 |
+
size=3
|
268 |
+
stride=1
|
269 |
+
pad=1
|
270 |
+
activation=leaky
|
271 |
+
|
272 |
+
[convolutional]
|
273 |
+
batch_normalize=1
|
274 |
+
filters=1024
|
275 |
+
size=1
|
276 |
+
stride=1
|
277 |
+
pad=1
|
278 |
+
activation=linear
|
279 |
+
|
280 |
+
[shortcut]
|
281 |
+
from=-4
|
282 |
+
activation=leaky
|
283 |
+
|
284 |
+
|
285 |
+
[convolutional]
|
286 |
+
batch_normalize=1
|
287 |
+
filters=128
|
288 |
+
size=1
|
289 |
+
stride=1
|
290 |
+
pad=1
|
291 |
+
activation=leaky
|
292 |
+
|
293 |
+
[convolutional]
|
294 |
+
groups = 32
|
295 |
+
batch_normalize=1
|
296 |
+
filters=128
|
297 |
+
size=3
|
298 |
+
stride=1
|
299 |
+
pad=1
|
300 |
+
activation=leaky
|
301 |
+
|
302 |
+
[convolutional]
|
303 |
+
batch_normalize=1
|
304 |
+
filters=1024
|
305 |
+
size=1
|
306 |
+
stride=1
|
307 |
+
pad=1
|
308 |
+
activation=linear
|
309 |
+
|
310 |
+
[shortcut]
|
311 |
+
from=-4
|
312 |
+
activation=leaky
|
313 |
+
|
314 |
+
|
315 |
+
[convolutional]
|
316 |
+
batch_normalize=1
|
317 |
+
filters=128
|
318 |
+
size=1
|
319 |
+
stride=1
|
320 |
+
pad=1
|
321 |
+
activation=leaky
|
322 |
+
|
323 |
+
[convolutional]
|
324 |
+
groups = 32
|
325 |
+
batch_normalize=1
|
326 |
+
filters=128
|
327 |
+
size=3
|
328 |
+
stride=1
|
329 |
+
pad=1
|
330 |
+
activation=leaky
|
331 |
+
|
332 |
+
[convolutional]
|
333 |
+
batch_normalize=1
|
334 |
+
filters=1024
|
335 |
+
size=1
|
336 |
+
stride=1
|
337 |
+
pad=1
|
338 |
+
activation=linear
|
339 |
+
|
340 |
+
[shortcut]
|
341 |
+
from=-4
|
342 |
+
activation=leaky
|
343 |
+
|
344 |
+
|
345 |
+
[convolutional]
|
346 |
+
batch_normalize=1
|
347 |
+
filters=128
|
348 |
+
size=1
|
349 |
+
stride=1
|
350 |
+
pad=1
|
351 |
+
activation=leaky
|
352 |
+
|
353 |
+
[convolutional]
|
354 |
+
groups = 32
|
355 |
+
batch_normalize=1
|
356 |
+
filters=128
|
357 |
+
size=3
|
358 |
+
stride=1
|
359 |
+
pad=1
|
360 |
+
activation=leaky
|
361 |
+
|
362 |
+
[convolutional]
|
363 |
+
batch_normalize=1
|
364 |
+
filters=1024
|
365 |
+
size=1
|
366 |
+
stride=1
|
367 |
+
pad=1
|
368 |
+
activation=linear
|
369 |
+
|
370 |
+
[shortcut]
|
371 |
+
from=-4
|
372 |
+
activation=leaky
|
373 |
+
|
374 |
+
|
375 |
+
|
376 |
+
[convolutional]
|
377 |
+
batch_normalize=1
|
378 |
+
filters=256
|
379 |
+
size=1
|
380 |
+
stride=1
|
381 |
+
pad=1
|
382 |
+
activation=leaky
|
383 |
+
|
384 |
+
[convolutional]
|
385 |
+
groups = 32
|
386 |
+
batch_normalize=1
|
387 |
+
filters=256
|
388 |
+
size=3
|
389 |
+
stride=2
|
390 |
+
pad=1
|
391 |
+
activation=leaky
|
392 |
+
|
393 |
+
[convolutional]
|
394 |
+
batch_normalize=1
|
395 |
+
filters=2048
|
396 |
+
size=1
|
397 |
+
stride=1
|
398 |
+
pad=1
|
399 |
+
activation=linear
|
400 |
+
|
401 |
+
[shortcut]
|
402 |
+
from=-4
|
403 |
+
activation=leaky
|
404 |
+
|
405 |
+
|
406 |
+
|
407 |
+
[convolutional]
|
408 |
+
batch_normalize=1
|
409 |
+
filters=256
|
410 |
+
size=1
|
411 |
+
stride=1
|
412 |
+
pad=1
|
413 |
+
activation=leaky
|
414 |
+
|
415 |
+
[convolutional]
|
416 |
+
groups = 32
|
417 |
+
batch_normalize=1
|
418 |
+
filters=256
|
419 |
+
size=3
|
420 |
+
stride=1
|
421 |
+
pad=1
|
422 |
+
activation=leaky
|
423 |
+
|
424 |
+
[convolutional]
|
425 |
+
batch_normalize=1
|
426 |
+
filters=2048
|
427 |
+
size=1
|
428 |
+
stride=1
|
429 |
+
pad=1
|
430 |
+
activation=linear
|
431 |
+
|
432 |
+
[shortcut]
|
433 |
+
from=-4
|
434 |
+
activation=leaky
|
435 |
+
|
436 |
+
|
437 |
+
[convolutional]
|
438 |
+
batch_normalize=1
|
439 |
+
filters=256
|
440 |
+
size=1
|
441 |
+
stride=1
|
442 |
+
pad=1
|
443 |
+
activation=leaky
|
444 |
+
|
445 |
+
[convolutional]
|
446 |
+
groups = 32
|
447 |
+
batch_normalize=1
|
448 |
+
filters=256
|
449 |
+
size=3
|
450 |
+
stride=1
|
451 |
+
pad=1
|
452 |
+
activation=leaky
|
453 |
+
|
454 |
+
[convolutional]
|
455 |
+
batch_normalize=1
|
456 |
+
filters=2048
|
457 |
+
size=1
|
458 |
+
stride=1
|
459 |
+
pad=1
|
460 |
+
activation=linear
|
461 |
+
|
462 |
+
[shortcut]
|
463 |
+
from=-4
|
464 |
+
activation=leaky
|
465 |
+
|
466 |
+
|
467 |
+
[convolutional]
|
468 |
+
batch_normalize=1
|
469 |
+
filters=256
|
470 |
+
size=1
|
471 |
+
stride=1
|
472 |
+
pad=1
|
473 |
+
activation=leaky
|
474 |
+
|
475 |
+
[convolutional]
|
476 |
+
groups = 32
|
477 |
+
batch_normalize=1
|
478 |
+
filters=256
|
479 |
+
size=3
|
480 |
+
stride=1
|
481 |
+
pad=1
|
482 |
+
activation=leaky
|
483 |
+
|
484 |
+
[convolutional]
|
485 |
+
batch_normalize=1
|
486 |
+
filters=2048
|
487 |
+
size=1
|
488 |
+
stride=1
|
489 |
+
pad=1
|
490 |
+
activation=linear
|
491 |
+
|
492 |
+
[shortcut]
|
493 |
+
from=-4
|
494 |
+
activation=leaky
|
495 |
+
|
496 |
+
|
497 |
+
[convolutional]
|
498 |
+
batch_normalize=1
|
499 |
+
filters=256
|
500 |
+
size=1
|
501 |
+
stride=1
|
502 |
+
pad=1
|
503 |
+
activation=leaky
|
504 |
+
|
505 |
+
[convolutional]
|
506 |
+
groups = 32
|
507 |
+
batch_normalize=1
|
508 |
+
filters=256
|
509 |
+
size=3
|
510 |
+
stride=1
|
511 |
+
pad=1
|
512 |
+
activation=leaky
|
513 |
+
|
514 |
+
[convolutional]
|
515 |
+
batch_normalize=1
|
516 |
+
filters=2048
|
517 |
+
size=1
|
518 |
+
stride=1
|
519 |
+
pad=1
|
520 |
+
activation=linear
|
521 |
+
|
522 |
+
[shortcut]
|
523 |
+
from=-4
|
524 |
+
activation=leaky
|
525 |
+
|
526 |
+
|
527 |
+
[convolutional]
|
528 |
+
batch_normalize=1
|
529 |
+
filters=256
|
530 |
+
size=1
|
531 |
+
stride=1
|
532 |
+
pad=1
|
533 |
+
activation=leaky
|
534 |
+
|
535 |
+
[convolutional]
|
536 |
+
groups = 32
|
537 |
+
batch_normalize=1
|
538 |
+
filters=256
|
539 |
+
size=3
|
540 |
+
stride=1
|
541 |
+
pad=1
|
542 |
+
activation=leaky
|
543 |
+
|
544 |
+
[convolutional]
|
545 |
+
batch_normalize=1
|
546 |
+
filters=2048
|
547 |
+
size=1
|
548 |
+
stride=1
|
549 |
+
pad=1
|
550 |
+
activation=linear
|
551 |
+
|
552 |
+
[shortcut]
|
553 |
+
from=-4
|
554 |
+
activation=leaky
|
555 |
+
|
556 |
+
|
557 |
+
[convolutional]
|
558 |
+
batch_normalize=1
|
559 |
+
filters=256
|
560 |
+
size=1
|
561 |
+
stride=1
|
562 |
+
pad=1
|
563 |
+
activation=leaky
|
564 |
+
|
565 |
+
[convolutional]
|
566 |
+
groups = 32
|
567 |
+
batch_normalize=1
|
568 |
+
filters=256
|
569 |
+
size=3
|
570 |
+
stride=1
|
571 |
+
pad=1
|
572 |
+
activation=leaky
|
573 |
+
|
574 |
+
[convolutional]
|
575 |
+
batch_normalize=1
|
576 |
+
filters=2048
|
577 |
+
size=1
|
578 |
+
stride=1
|
579 |
+
pad=1
|
580 |
+
activation=linear
|
581 |
+
|
582 |
+
[shortcut]
|
583 |
+
from=-4
|
584 |
+
activation=leaky
|
585 |
+
|
586 |
+
|
587 |
+
[convolutional]
|
588 |
+
batch_normalize=1
|
589 |
+
filters=256
|
590 |
+
size=1
|
591 |
+
stride=1
|
592 |
+
pad=1
|
593 |
+
activation=leaky
|
594 |
+
|
595 |
+
[convolutional]
|
596 |
+
groups = 32
|
597 |
+
batch_normalize=1
|
598 |
+
filters=256
|
599 |
+
size=3
|
600 |
+
stride=1
|
601 |
+
pad=1
|
602 |
+
activation=leaky
|
603 |
+
|
604 |
+
[convolutional]
|
605 |
+
batch_normalize=1
|
606 |
+
filters=2048
|
607 |
+
size=1
|
608 |
+
stride=1
|
609 |
+
pad=1
|
610 |
+
activation=linear
|
611 |
+
|
612 |
+
[shortcut]
|
613 |
+
from=-4
|
614 |
+
activation=leaky
|
615 |
+
|
616 |
+
|
617 |
+
[convolutional]
|
618 |
+
batch_normalize=1
|
619 |
+
filters=256
|
620 |
+
size=1
|
621 |
+
stride=1
|
622 |
+
pad=1
|
623 |
+
activation=leaky
|
624 |
+
|
625 |
+
[convolutional]
|
626 |
+
groups = 32
|
627 |
+
batch_normalize=1
|
628 |
+
filters=256
|
629 |
+
size=3
|
630 |
+
stride=1
|
631 |
+
pad=1
|
632 |
+
activation=leaky
|
633 |
+
|
634 |
+
[convolutional]
|
635 |
+
batch_normalize=1
|
636 |
+
filters=2048
|
637 |
+
size=1
|
638 |
+
stride=1
|
639 |
+
pad=1
|
640 |
+
activation=linear
|
641 |
+
|
642 |
+
[shortcut]
|
643 |
+
from=-4
|
644 |
+
activation=leaky
|
645 |
+
|
646 |
+
|
647 |
+
[convolutional]
|
648 |
+
batch_normalize=1
|
649 |
+
filters=256
|
650 |
+
size=1
|
651 |
+
stride=1
|
652 |
+
pad=1
|
653 |
+
activation=leaky
|
654 |
+
|
655 |
+
[convolutional]
|
656 |
+
groups = 32
|
657 |
+
batch_normalize=1
|
658 |
+
filters=256
|
659 |
+
size=3
|
660 |
+
stride=1
|
661 |
+
pad=1
|
662 |
+
activation=leaky
|
663 |
+
|
664 |
+
[convolutional]
|
665 |
+
batch_normalize=1
|
666 |
+
filters=2048
|
667 |
+
size=1
|
668 |
+
stride=1
|
669 |
+
pad=1
|
670 |
+
activation=linear
|
671 |
+
|
672 |
+
[shortcut]
|
673 |
+
from=-4
|
674 |
+
activation=leaky
|
675 |
+
|
676 |
+
|
677 |
+
[convolutional]
|
678 |
+
batch_normalize=1
|
679 |
+
filters=256
|
680 |
+
size=1
|
681 |
+
stride=1
|
682 |
+
pad=1
|
683 |
+
activation=leaky
|
684 |
+
|
685 |
+
[convolutional]
|
686 |
+
groups = 32
|
687 |
+
batch_normalize=1
|
688 |
+
filters=256
|
689 |
+
size=3
|
690 |
+
stride=1
|
691 |
+
pad=1
|
692 |
+
activation=leaky
|
693 |
+
|
694 |
+
[convolutional]
|
695 |
+
batch_normalize=1
|
696 |
+
filters=2048
|
697 |
+
size=1
|
698 |
+
stride=1
|
699 |
+
pad=1
|
700 |
+
activation=linear
|
701 |
+
|
702 |
+
[shortcut]
|
703 |
+
from=-4
|
704 |
+
activation=leaky
|
705 |
+
|
706 |
+
|
707 |
+
[convolutional]
|
708 |
+
batch_normalize=1
|
709 |
+
filters=256
|
710 |
+
size=1
|
711 |
+
stride=1
|
712 |
+
pad=1
|
713 |
+
activation=leaky
|
714 |
+
|
715 |
+
[convolutional]
|
716 |
+
groups = 32
|
717 |
+
batch_normalize=1
|
718 |
+
filters=256
|
719 |
+
size=3
|
720 |
+
stride=1
|
721 |
+
pad=1
|
722 |
+
activation=leaky
|
723 |
+
|
724 |
+
[convolutional]
|
725 |
+
batch_normalize=1
|
726 |
+
filters=2048
|
727 |
+
size=1
|
728 |
+
stride=1
|
729 |
+
pad=1
|
730 |
+
activation=linear
|
731 |
+
|
732 |
+
[shortcut]
|
733 |
+
from=-4
|
734 |
+
activation=leaky
|
735 |
+
|
736 |
+
|
737 |
+
[convolutional]
|
738 |
+
batch_normalize=1
|
739 |
+
filters=256
|
740 |
+
size=1
|
741 |
+
stride=1
|
742 |
+
pad=1
|
743 |
+
activation=leaky
|
744 |
+
|
745 |
+
[convolutional]
|
746 |
+
groups = 32
|
747 |
+
batch_normalize=1
|
748 |
+
filters=256
|
749 |
+
size=3
|
750 |
+
stride=1
|
751 |
+
pad=1
|
752 |
+
activation=leaky
|
753 |
+
|
754 |
+
[convolutional]
|
755 |
+
batch_normalize=1
|
756 |
+
filters=2048
|
757 |
+
size=1
|
758 |
+
stride=1
|
759 |
+
pad=1
|
760 |
+
activation=linear
|
761 |
+
|
762 |
+
[shortcut]
|
763 |
+
from=-4
|
764 |
+
activation=leaky
|
765 |
+
|
766 |
+
|
767 |
+
[convolutional]
|
768 |
+
batch_normalize=1
|
769 |
+
filters=256
|
770 |
+
size=1
|
771 |
+
stride=1
|
772 |
+
pad=1
|
773 |
+
activation=leaky
|
774 |
+
|
775 |
+
[convolutional]
|
776 |
+
groups = 32
|
777 |
+
batch_normalize=1
|
778 |
+
filters=256
|
779 |
+
size=3
|
780 |
+
stride=1
|
781 |
+
pad=1
|
782 |
+
activation=leaky
|
783 |
+
|
784 |
+
[convolutional]
|
785 |
+
batch_normalize=1
|
786 |
+
filters=2048
|
787 |
+
size=1
|
788 |
+
stride=1
|
789 |
+
pad=1
|
790 |
+
activation=linear
|
791 |
+
|
792 |
+
[shortcut]
|
793 |
+
from=-4
|
794 |
+
activation=leaky
|
795 |
+
|
796 |
+
|
797 |
+
[convolutional]
|
798 |
+
batch_normalize=1
|
799 |
+
filters=256
|
800 |
+
size=1
|
801 |
+
stride=1
|
802 |
+
pad=1
|
803 |
+
activation=leaky
|
804 |
+
|
805 |
+
[convolutional]
|
806 |
+
groups = 32
|
807 |
+
batch_normalize=1
|
808 |
+
filters=256
|
809 |
+
size=3
|
810 |
+
stride=1
|
811 |
+
pad=1
|
812 |
+
activation=leaky
|
813 |
+
|
814 |
+
[convolutional]
|
815 |
+
batch_normalize=1
|
816 |
+
filters=2048
|
817 |
+
size=1
|
818 |
+
stride=1
|
819 |
+
pad=1
|
820 |
+
activation=linear
|
821 |
+
|
822 |
+
[shortcut]
|
823 |
+
from=-4
|
824 |
+
activation=leaky
|
825 |
+
|
826 |
+
|
827 |
+
[convolutional]
|
828 |
+
batch_normalize=1
|
829 |
+
filters=256
|
830 |
+
size=1
|
831 |
+
stride=1
|
832 |
+
pad=1
|
833 |
+
activation=leaky
|
834 |
+
|
835 |
+
[convolutional]
|
836 |
+
groups = 32
|
837 |
+
batch_normalize=1
|
838 |
+
filters=256
|
839 |
+
size=3
|
840 |
+
stride=1
|
841 |
+
pad=1
|
842 |
+
activation=leaky
|
843 |
+
|
844 |
+
[convolutional]
|
845 |
+
batch_normalize=1
|
846 |
+
filters=2048
|
847 |
+
size=1
|
848 |
+
stride=1
|
849 |
+
pad=1
|
850 |
+
activation=linear
|
851 |
+
|
852 |
+
[shortcut]
|
853 |
+
from=-4
|
854 |
+
activation=leaky
|
855 |
+
|
856 |
+
|
857 |
+
[convolutional]
|
858 |
+
batch_normalize=1
|
859 |
+
filters=256
|
860 |
+
size=1
|
861 |
+
stride=1
|
862 |
+
pad=1
|
863 |
+
activation=leaky
|
864 |
+
|
865 |
+
[convolutional]
|
866 |
+
groups = 32
|
867 |
+
batch_normalize=1
|
868 |
+
filters=256
|
869 |
+
size=3
|
870 |
+
stride=1
|
871 |
+
pad=1
|
872 |
+
activation=leaky
|
873 |
+
|
874 |
+
[convolutional]
|
875 |
+
batch_normalize=1
|
876 |
+
filters=2048
|
877 |
+
size=1
|
878 |
+
stride=1
|
879 |
+
pad=1
|
880 |
+
activation=linear
|
881 |
+
|
882 |
+
[shortcut]
|
883 |
+
from=-4
|
884 |
+
activation=leaky
|
885 |
+
|
886 |
+
|
887 |
+
[convolutional]
|
888 |
+
batch_normalize=1
|
889 |
+
filters=256
|
890 |
+
size=1
|
891 |
+
stride=1
|
892 |
+
pad=1
|
893 |
+
activation=leaky
|
894 |
+
|
895 |
+
[convolutional]
|
896 |
+
groups = 32
|
897 |
+
batch_normalize=1
|
898 |
+
filters=256
|
899 |
+
size=3
|
900 |
+
stride=1
|
901 |
+
pad=1
|
902 |
+
activation=leaky
|
903 |
+
|
904 |
+
[convolutional]
|
905 |
+
batch_normalize=1
|
906 |
+
filters=2048
|
907 |
+
size=1
|
908 |
+
stride=1
|
909 |
+
pad=1
|
910 |
+
activation=linear
|
911 |
+
|
912 |
+
[shortcut]
|
913 |
+
from=-4
|
914 |
+
activation=leaky
|
915 |
+
|
916 |
+
|
917 |
+
[convolutional]
|
918 |
+
batch_normalize=1
|
919 |
+
filters=256
|
920 |
+
size=1
|
921 |
+
stride=1
|
922 |
+
pad=1
|
923 |
+
activation=leaky
|
924 |
+
|
925 |
+
[convolutional]
|
926 |
+
groups = 32
|
927 |
+
batch_normalize=1
|
928 |
+
filters=256
|
929 |
+
size=3
|
930 |
+
stride=1
|
931 |
+
pad=1
|
932 |
+
activation=leaky
|
933 |
+
|
934 |
+
[convolutional]
|
935 |
+
batch_normalize=1
|
936 |
+
filters=2048
|
937 |
+
size=1
|
938 |
+
stride=1
|
939 |
+
pad=1
|
940 |
+
activation=linear
|
941 |
+
|
942 |
+
[shortcut]
|
943 |
+
from=-4
|
944 |
+
activation=leaky
|
945 |
+
|
946 |
+
|
947 |
+
[convolutional]
|
948 |
+
batch_normalize=1
|
949 |
+
filters=256
|
950 |
+
size=1
|
951 |
+
stride=1
|
952 |
+
pad=1
|
953 |
+
activation=leaky
|
954 |
+
|
955 |
+
[convolutional]
|
956 |
+
groups = 32
|
957 |
+
batch_normalize=1
|
958 |
+
filters=256
|
959 |
+
size=3
|
960 |
+
stride=1
|
961 |
+
pad=1
|
962 |
+
activation=leaky
|
963 |
+
|
964 |
+
[convolutional]
|
965 |
+
batch_normalize=1
|
966 |
+
filters=2048
|
967 |
+
size=1
|
968 |
+
stride=1
|
969 |
+
pad=1
|
970 |
+
activation=linear
|
971 |
+
|
972 |
+
[shortcut]
|
973 |
+
from=-4
|
974 |
+
activation=leaky
|
975 |
+
|
976 |
+
|
977 |
+
[convolutional]
|
978 |
+
batch_normalize=1
|
979 |
+
filters=256
|
980 |
+
size=1
|
981 |
+
stride=1
|
982 |
+
pad=1
|
983 |
+
activation=leaky
|
984 |
+
|
985 |
+
[convolutional]
|
986 |
+
groups = 32
|
987 |
+
batch_normalize=1
|
988 |
+
filters=256
|
989 |
+
size=3
|
990 |
+
stride=1
|
991 |
+
pad=1
|
992 |
+
activation=leaky
|
993 |
+
|
994 |
+
[convolutional]
|
995 |
+
batch_normalize=1
|
996 |
+
filters=2048
|
997 |
+
size=1
|
998 |
+
stride=1
|
999 |
+
pad=1
|
1000 |
+
activation=linear
|
1001 |
+
|
1002 |
+
[shortcut]
|
1003 |
+
from=-4
|
1004 |
+
activation=leaky
|
1005 |
+
|
1006 |
+
|
1007 |
+
[convolutional]
|
1008 |
+
batch_normalize=1
|
1009 |
+
filters=256
|
1010 |
+
size=1
|
1011 |
+
stride=1
|
1012 |
+
pad=1
|
1013 |
+
activation=leaky
|
1014 |
+
|
1015 |
+
[convolutional]
|
1016 |
+
groups = 32
|
1017 |
+
batch_normalize=1
|
1018 |
+
filters=256
|
1019 |
+
size=3
|
1020 |
+
stride=1
|
1021 |
+
pad=1
|
1022 |
+
activation=leaky
|
1023 |
+
|
1024 |
+
[convolutional]
|
1025 |
+
batch_normalize=1
|
1026 |
+
filters=2048
|
1027 |
+
size=1
|
1028 |
+
stride=1
|
1029 |
+
pad=1
|
1030 |
+
activation=linear
|
1031 |
+
|
1032 |
+
[shortcut]
|
1033 |
+
from=-4
|
1034 |
+
activation=leaky
|
1035 |
+
|
1036 |
+
|
1037 |
+
[convolutional]
|
1038 |
+
batch_normalize=1
|
1039 |
+
filters=256
|
1040 |
+
size=1
|
1041 |
+
stride=1
|
1042 |
+
pad=1
|
1043 |
+
activation=leaky
|
1044 |
+
|
1045 |
+
[convolutional]
|
1046 |
+
groups = 32
|
1047 |
+
batch_normalize=1
|
1048 |
+
filters=256
|
1049 |
+
size=3
|
1050 |
+
stride=1
|
1051 |
+
pad=1
|
1052 |
+
activation=leaky
|
1053 |
+
|
1054 |
+
[convolutional]
|
1055 |
+
batch_normalize=1
|
1056 |
+
filters=2048
|
1057 |
+
size=1
|
1058 |
+
stride=1
|
1059 |
+
pad=1
|
1060 |
+
activation=linear
|
1061 |
+
|
1062 |
+
[shortcut]
|
1063 |
+
from=-4
|
1064 |
+
activation=leaky
|
1065 |
+
|
1066 |
+
|
1067 |
+
[convolutional]
|
1068 |
+
batch_normalize=1
|
1069 |
+
filters=256
|
1070 |
+
size=1
|
1071 |
+
stride=1
|
1072 |
+
pad=1
|
1073 |
+
activation=leaky
|
1074 |
+
|
1075 |
+
[convolutional]
|
1076 |
+
groups = 32
|
1077 |
+
batch_normalize=1
|
1078 |
+
filters=256
|
1079 |
+
size=3
|
1080 |
+
stride=1
|
1081 |
+
pad=1
|
1082 |
+
activation=leaky
|
1083 |
+
|
1084 |
+
[convolutional]
|
1085 |
+
batch_normalize=1
|
1086 |
+
filters=2048
|
1087 |
+
size=1
|
1088 |
+
stride=1
|
1089 |
+
pad=1
|
1090 |
+
activation=linear
|
1091 |
+
|
1092 |
+
[shortcut]
|
1093 |
+
from=-4
|
1094 |
+
activation=leaky
|
1095 |
+
|
1096 |
+
|
1097 |
+
[convolutional]
|
1098 |
+
batch_normalize=1
|
1099 |
+
filters=256
|
1100 |
+
size=1
|
1101 |
+
stride=1
|
1102 |
+
pad=1
|
1103 |
+
activation=leaky
|
1104 |
+
|
1105 |
+
[convolutional]
|
1106 |
+
groups = 32
|
1107 |
+
batch_normalize=1
|
1108 |
+
filters=256
|
1109 |
+
size=3
|
1110 |
+
stride=1
|
1111 |
+
pad=1
|
1112 |
+
activation=leaky
|
1113 |
+
|
1114 |
+
[convolutional]
|
1115 |
+
batch_normalize=1
|
1116 |
+
filters=2048
|
1117 |
+
size=1
|
1118 |
+
stride=1
|
1119 |
+
pad=1
|
1120 |
+
activation=linear
|
1121 |
+
|
1122 |
+
[shortcut]
|
1123 |
+
from=-4
|
1124 |
+
activation=leaky
|
1125 |
+
|
1126 |
+
|
1127 |
+
[convolutional]
|
1128 |
+
batch_normalize=1
|
1129 |
+
filters=256
|
1130 |
+
size=1
|
1131 |
+
stride=1
|
1132 |
+
pad=1
|
1133 |
+
activation=leaky
|
1134 |
+
|
1135 |
+
[convolutional]
|
1136 |
+
groups = 32
|
1137 |
+
batch_normalize=1
|
1138 |
+
filters=256
|
1139 |
+
size=3
|
1140 |
+
stride=1
|
1141 |
+
pad=1
|
1142 |
+
activation=leaky
|
1143 |
+
|
1144 |
+
[convolutional]
|
1145 |
+
batch_normalize=1
|
1146 |
+
filters=2048
|
1147 |
+
size=1
|
1148 |
+
stride=1
|
1149 |
+
pad=1
|
1150 |
+
activation=linear
|
1151 |
+
|
1152 |
+
[shortcut]
|
1153 |
+
from=-4
|
1154 |
+
activation=leaky
|
1155 |
+
|
1156 |
+
|
1157 |
+
[convolutional]
|
1158 |
+
batch_normalize=1
|
1159 |
+
filters=256
|
1160 |
+
size=1
|
1161 |
+
stride=1
|
1162 |
+
pad=1
|
1163 |
+
activation=leaky
|
1164 |
+
|
1165 |
+
[convolutional]
|
1166 |
+
groups = 32
|
1167 |
+
batch_normalize=1
|
1168 |
+
filters=256
|
1169 |
+
size=3
|
1170 |
+
stride=1
|
1171 |
+
pad=1
|
1172 |
+
activation=leaky
|
1173 |
+
|
1174 |
+
[convolutional]
|
1175 |
+
batch_normalize=1
|
1176 |
+
filters=2048
|
1177 |
+
size=1
|
1178 |
+
stride=1
|
1179 |
+
pad=1
|
1180 |
+
activation=linear
|
1181 |
+
|
1182 |
+
[shortcut]
|
1183 |
+
from=-4
|
1184 |
+
activation=leaky
|
1185 |
+
|
1186 |
+
|
1187 |
+
[convolutional]
|
1188 |
+
batch_normalize=1
|
1189 |
+
filters=256
|
1190 |
+
size=1
|
1191 |
+
stride=1
|
1192 |
+
pad=1
|
1193 |
+
activation=leaky
|
1194 |
+
|
1195 |
+
[convolutional]
|
1196 |
+
groups = 32
|
1197 |
+
batch_normalize=1
|
1198 |
+
filters=256
|
1199 |
+
size=3
|
1200 |
+
stride=1
|
1201 |
+
pad=1
|
1202 |
+
activation=leaky
|
1203 |
+
|
1204 |
+
[convolutional]
|
1205 |
+
batch_normalize=1
|
1206 |
+
filters=2048
|
1207 |
+
size=1
|
1208 |
+
stride=1
|
1209 |
+
pad=1
|
1210 |
+
activation=linear
|
1211 |
+
|
1212 |
+
[shortcut]
|
1213 |
+
from=-4
|
1214 |
+
activation=leaky
|
1215 |
+
|
1216 |
+
|
1217 |
+
[convolutional]
|
1218 |
+
batch_normalize=1
|
1219 |
+
filters=256
|
1220 |
+
size=1
|
1221 |
+
stride=1
|
1222 |
+
pad=1
|
1223 |
+
activation=leaky
|
1224 |
+
|
1225 |
+
[convolutional]
|
1226 |
+
groups = 32
|
1227 |
+
batch_normalize=1
|
1228 |
+
filters=256
|
1229 |
+
size=3
|
1230 |
+
stride=1
|
1231 |
+
pad=1
|
1232 |
+
activation=leaky
|
1233 |
+
|
1234 |
+
[convolutional]
|
1235 |
+
batch_normalize=1
|
1236 |
+
filters=2048
|
1237 |
+
size=1
|
1238 |
+
stride=1
|
1239 |
+
pad=1
|
1240 |
+
activation=linear
|
1241 |
+
|
1242 |
+
[shortcut]
|
1243 |
+
from=-4
|
1244 |
+
activation=leaky
|
1245 |
+
|
1246 |
+
|
1247 |
+
[convolutional]
|
1248 |
+
batch_normalize=1
|
1249 |
+
filters=256
|
1250 |
+
size=1
|
1251 |
+
stride=1
|
1252 |
+
pad=1
|
1253 |
+
activation=leaky
|
1254 |
+
|
1255 |
+
[convolutional]
|
1256 |
+
groups = 32
|
1257 |
+
batch_normalize=1
|
1258 |
+
filters=256
|
1259 |
+
size=3
|
1260 |
+
stride=1
|
1261 |
+
pad=1
|
1262 |
+
activation=leaky
|
1263 |
+
|
1264 |
+
[convolutional]
|
1265 |
+
batch_normalize=1
|
1266 |
+
filters=2048
|
1267 |
+
size=1
|
1268 |
+
stride=1
|
1269 |
+
pad=1
|
1270 |
+
activation=linear
|
1271 |
+
|
1272 |
+
[shortcut]
|
1273 |
+
from=-4
|
1274 |
+
activation=leaky
|
1275 |
+
|
1276 |
+
|
1277 |
+
[convolutional]
|
1278 |
+
batch_normalize=1
|
1279 |
+
filters=256
|
1280 |
+
size=1
|
1281 |
+
stride=1
|
1282 |
+
pad=1
|
1283 |
+
activation=leaky
|
1284 |
+
|
1285 |
+
[convolutional]
|
1286 |
+
groups = 32
|
1287 |
+
batch_normalize=1
|
1288 |
+
filters=256
|
1289 |
+
size=3
|
1290 |
+
stride=1
|
1291 |
+
pad=1
|
1292 |
+
activation=leaky
|
1293 |
+
|
1294 |
+
[convolutional]
|
1295 |
+
batch_normalize=1
|
1296 |
+
filters=2048
|
1297 |
+
size=1
|
1298 |
+
stride=1
|
1299 |
+
pad=1
|
1300 |
+
activation=linear
|
1301 |
+
|
1302 |
+
[shortcut]
|
1303 |
+
from=-4
|
1304 |
+
activation=leaky
|
1305 |
+
|
1306 |
+
|
1307 |
+
[convolutional]
|
1308 |
+
batch_normalize=1
|
1309 |
+
filters=256
|
1310 |
+
size=1
|
1311 |
+
stride=1
|
1312 |
+
pad=1
|
1313 |
+
activation=leaky
|
1314 |
+
|
1315 |
+
[convolutional]
|
1316 |
+
groups = 32
|
1317 |
+
batch_normalize=1
|
1318 |
+
filters=256
|
1319 |
+
size=3
|
1320 |
+
stride=1
|
1321 |
+
pad=1
|
1322 |
+
activation=leaky
|
1323 |
+
|
1324 |
+
[convolutional]
|
1325 |
+
batch_normalize=1
|
1326 |
+
filters=2048
|
1327 |
+
size=1
|
1328 |
+
stride=1
|
1329 |
+
pad=1
|
1330 |
+
activation=linear
|
1331 |
+
|
1332 |
+
[shortcut]
|
1333 |
+
from=-4
|
1334 |
+
activation=leaky
|
1335 |
+
|
1336 |
+
|
1337 |
+
[convolutional]
|
1338 |
+
batch_normalize=1
|
1339 |
+
filters=256
|
1340 |
+
size=1
|
1341 |
+
stride=1
|
1342 |
+
pad=1
|
1343 |
+
activation=leaky
|
1344 |
+
|
1345 |
+
[convolutional]
|
1346 |
+
groups = 32
|
1347 |
+
batch_normalize=1
|
1348 |
+
filters=256
|
1349 |
+
size=3
|
1350 |
+
stride=1
|
1351 |
+
pad=1
|
1352 |
+
activation=leaky
|
1353 |
+
|
1354 |
+
[convolutional]
|
1355 |
+
batch_normalize=1
|
1356 |
+
filters=2048
|
1357 |
+
size=1
|
1358 |
+
stride=1
|
1359 |
+
pad=1
|
1360 |
+
activation=linear
|
1361 |
+
|
1362 |
+
[shortcut]
|
1363 |
+
from=-4
|
1364 |
+
activation=leaky
|
1365 |
+
|
1366 |
+
|
1367 |
+
[convolutional]
|
1368 |
+
batch_normalize=1
|
1369 |
+
filters=256
|
1370 |
+
size=1
|
1371 |
+
stride=1
|
1372 |
+
pad=1
|
1373 |
+
activation=leaky
|
1374 |
+
|
1375 |
+
[convolutional]
|
1376 |
+
groups = 32
|
1377 |
+
batch_normalize=1
|
1378 |
+
filters=256
|
1379 |
+
size=3
|
1380 |
+
stride=1
|
1381 |
+
pad=1
|
1382 |
+
activation=leaky
|
1383 |
+
|
1384 |
+
[convolutional]
|
1385 |
+
batch_normalize=1
|
1386 |
+
filters=2048
|
1387 |
+
size=1
|
1388 |
+
stride=1
|
1389 |
+
pad=1
|
1390 |
+
activation=linear
|
1391 |
+
|
1392 |
+
[shortcut]
|
1393 |
+
from=-4
|
1394 |
+
activation=leaky
|
1395 |
+
|
1396 |
+
|
1397 |
+
[convolutional]
|
1398 |
+
batch_normalize=1
|
1399 |
+
filters=256
|
1400 |
+
size=1
|
1401 |
+
stride=1
|
1402 |
+
pad=1
|
1403 |
+
activation=leaky
|
1404 |
+
|
1405 |
+
[convolutional]
|
1406 |
+
groups = 32
|
1407 |
+
batch_normalize=1
|
1408 |
+
filters=256
|
1409 |
+
size=3
|
1410 |
+
stride=1
|
1411 |
+
pad=1
|
1412 |
+
activation=leaky
|
1413 |
+
|
1414 |
+
[convolutional]
|
1415 |
+
batch_normalize=1
|
1416 |
+
filters=2048
|
1417 |
+
size=1
|
1418 |
+
stride=1
|
1419 |
+
pad=1
|
1420 |
+
activation=linear
|
1421 |
+
|
1422 |
+
[shortcut]
|
1423 |
+
from=-4
|
1424 |
+
activation=leaky
|
1425 |
+
|
1426 |
+
|
1427 |
+
[convolutional]
|
1428 |
+
batch_normalize=1
|
1429 |
+
filters=256
|
1430 |
+
size=1
|
1431 |
+
stride=1
|
1432 |
+
pad=1
|
1433 |
+
activation=leaky
|
1434 |
+
|
1435 |
+
[convolutional]
|
1436 |
+
groups = 32
|
1437 |
+
batch_normalize=1
|
1438 |
+
filters=256
|
1439 |
+
size=3
|
1440 |
+
stride=1
|
1441 |
+
pad=1
|
1442 |
+
activation=leaky
|
1443 |
+
|
1444 |
+
[convolutional]
|
1445 |
+
batch_normalize=1
|
1446 |
+
filters=2048
|
1447 |
+
size=1
|
1448 |
+
stride=1
|
1449 |
+
pad=1
|
1450 |
+
activation=linear
|
1451 |
+
|
1452 |
+
[shortcut]
|
1453 |
+
from=-4
|
1454 |
+
activation=leaky
|
1455 |
+
|
1456 |
+
|
1457 |
+
|
1458 |
+
[convolutional]
|
1459 |
+
batch_normalize=1
|
1460 |
+
filters=512
|
1461 |
+
size=1
|
1462 |
+
stride=1
|
1463 |
+
pad=1
|
1464 |
+
activation=leaky
|
1465 |
+
|
1466 |
+
[convolutional]
|
1467 |
+
groups = 32
|
1468 |
+
batch_normalize=1
|
1469 |
+
filters=512
|
1470 |
+
size=3
|
1471 |
+
stride=2
|
1472 |
+
pad=1
|
1473 |
+
activation=leaky
|
1474 |
+
|
1475 |
+
[convolutional]
|
1476 |
+
batch_normalize=1
|
1477 |
+
filters=4096
|
1478 |
+
size=1
|
1479 |
+
stride=1
|
1480 |
+
pad=1
|
1481 |
+
activation=linear
|
1482 |
+
|
1483 |
+
[shortcut]
|
1484 |
+
from=-4
|
1485 |
+
activation=leaky
|
1486 |
+
|
1487 |
+
|
1488 |
+
|
1489 |
+
[convolutional]
|
1490 |
+
batch_normalize=1
|
1491 |
+
filters=512
|
1492 |
+
size=1
|
1493 |
+
stride=1
|
1494 |
+
pad=1
|
1495 |
+
activation=leaky
|
1496 |
+
|
1497 |
+
[convolutional]
|
1498 |
+
groups = 32
|
1499 |
+
batch_normalize=1
|
1500 |
+
filters=512
|
1501 |
+
size=3
|
1502 |
+
stride=1
|
1503 |
+
pad=1
|
1504 |
+
activation=leaky
|
1505 |
+
|
1506 |
+
[convolutional]
|
1507 |
+
batch_normalize=1
|
1508 |
+
filters=4096
|
1509 |
+
size=1
|
1510 |
+
stride=1
|
1511 |
+
pad=1
|
1512 |
+
activation=linear
|
1513 |
+
|
1514 |
+
[shortcut]
|
1515 |
+
from=-4
|
1516 |
+
activation=leaky
|
1517 |
+
|
1518 |
+
|
1519 |
+
[convolutional]
|
1520 |
+
batch_normalize=1
|
1521 |
+
filters=512
|
1522 |
+
size=1
|
1523 |
+
stride=1
|
1524 |
+
pad=1
|
1525 |
+
activation=leaky
|
1526 |
+
|
1527 |
+
[convolutional]
|
1528 |
+
groups = 32
|
1529 |
+
batch_normalize=1
|
1530 |
+
filters=512
|
1531 |
+
size=3
|
1532 |
+
stride=1
|
1533 |
+
pad=1
|
1534 |
+
activation=leaky
|
1535 |
+
|
1536 |
+
[convolutional]
|
1537 |
+
batch_normalize=1
|
1538 |
+
filters=4096
|
1539 |
+
size=1
|
1540 |
+
stride=1
|
1541 |
+
pad=1
|
1542 |
+
activation=linear
|
1543 |
+
|
1544 |
+
[shortcut]
|
1545 |
+
from=-4
|
1546 |
+
activation=leaky
|
1547 |
+
|
1548 |
+
|
1549 |
+
|
1550 |
+
|
1551 |
+
[avgpool]
|
1552 |
+
|
1553 |
+
[convolutional]
|
1554 |
+
filters=1000
|
1555 |
+
size=1
|
1556 |
+
stride=1
|
1557 |
+
pad=1
|
1558 |
+
activation=linear
|
1559 |
+
|
1560 |
+
[softmax]
|
1561 |
+
groups=1
|
1562 |
+
|
model/cfg/resnext50.cfg
ADDED
@@ -0,0 +1,523 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=4
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
channels=3
|
13 |
+
min_crop=128
|
14 |
+
max_crop=448
|
15 |
+
|
16 |
+
burn_in=1000
|
17 |
+
learning_rate=0.1
|
18 |
+
policy=poly
|
19 |
+
power=4
|
20 |
+
max_batches=800000
|
21 |
+
momentum=0.9
|
22 |
+
decay=0.0005
|
23 |
+
|
24 |
+
angle=7
|
25 |
+
hue=.1
|
26 |
+
saturation=.75
|
27 |
+
exposure=.75
|
28 |
+
aspect=.75
|
29 |
+
|
30 |
+
|
31 |
+
|
32 |
+
[convolutional]
|
33 |
+
batch_normalize=1
|
34 |
+
filters=64
|
35 |
+
size=7
|
36 |
+
stride=2
|
37 |
+
pad=1
|
38 |
+
activation=leaky
|
39 |
+
|
40 |
+
[maxpool]
|
41 |
+
size=2
|
42 |
+
stride=2
|
43 |
+
|
44 |
+
[convolutional]
|
45 |
+
batch_normalize=1
|
46 |
+
filters=128
|
47 |
+
size=1
|
48 |
+
stride=1
|
49 |
+
pad=1
|
50 |
+
activation=leaky
|
51 |
+
|
52 |
+
[convolutional]
|
53 |
+
batch_normalize=1
|
54 |
+
filters=128
|
55 |
+
size=3
|
56 |
+
groups=32
|
57 |
+
stride=1
|
58 |
+
pad=1
|
59 |
+
activation=leaky
|
60 |
+
|
61 |
+
[convolutional]
|
62 |
+
batch_normalize=1
|
63 |
+
filters=256
|
64 |
+
size=1
|
65 |
+
stride=1
|
66 |
+
pad=1
|
67 |
+
activation=linear
|
68 |
+
|
69 |
+
[shortcut]
|
70 |
+
from=-4
|
71 |
+
activation=leaky
|
72 |
+
|
73 |
+
[convolutional]
|
74 |
+
batch_normalize=1
|
75 |
+
filters=128
|
76 |
+
size=1
|
77 |
+
stride=1
|
78 |
+
pad=1
|
79 |
+
activation=leaky
|
80 |
+
|
81 |
+
[convolutional]
|
82 |
+
batch_normalize=1
|
83 |
+
filters=128
|
84 |
+
size=3
|
85 |
+
groups=32
|
86 |
+
stride=1
|
87 |
+
pad=1
|
88 |
+
activation=leaky
|
89 |
+
|
90 |
+
[convolutional]
|
91 |
+
batch_normalize=1
|
92 |
+
filters=256
|
93 |
+
size=1
|
94 |
+
stride=1
|
95 |
+
pad=1
|
96 |
+
activation=linear
|
97 |
+
|
98 |
+
[shortcut]
|
99 |
+
from=-4
|
100 |
+
activation=leaky
|
101 |
+
|
102 |
+
[convolutional]
|
103 |
+
batch_normalize=1
|
104 |
+
filters=128
|
105 |
+
size=1
|
106 |
+
stride=1
|
107 |
+
pad=1
|
108 |
+
activation=leaky
|
109 |
+
|
110 |
+
[convolutional]
|
111 |
+
batch_normalize=1
|
112 |
+
filters=128
|
113 |
+
size=3
|
114 |
+
groups=32
|
115 |
+
stride=1
|
116 |
+
pad=1
|
117 |
+
activation=leaky
|
118 |
+
|
119 |
+
[convolutional]
|
120 |
+
batch_normalize=1
|
121 |
+
filters=256
|
122 |
+
size=1
|
123 |
+
stride=1
|
124 |
+
pad=1
|
125 |
+
activation=linear
|
126 |
+
|
127 |
+
[shortcut]
|
128 |
+
from=-4
|
129 |
+
activation=leaky
|
130 |
+
|
131 |
+
[convolutional]
|
132 |
+
batch_normalize=1
|
133 |
+
filters=256
|
134 |
+
size=1
|
135 |
+
stride=1
|
136 |
+
pad=1
|
137 |
+
activation=leaky
|
138 |
+
|
139 |
+
[convolutional]
|
140 |
+
batch_normalize=1
|
141 |
+
filters=256
|
142 |
+
size=3
|
143 |
+
groups=32
|
144 |
+
stride=2
|
145 |
+
pad=1
|
146 |
+
activation=leaky
|
147 |
+
|
148 |
+
[convolutional]
|
149 |
+
batch_normalize=1
|
150 |
+
filters=512
|
151 |
+
size=1
|
152 |
+
stride=1
|
153 |
+
pad=1
|
154 |
+
activation=linear
|
155 |
+
|
156 |
+
[shortcut]
|
157 |
+
from=-4
|
158 |
+
activation=leaky
|
159 |
+
|
160 |
+
[convolutional]
|
161 |
+
batch_normalize=1
|
162 |
+
filters=256
|
163 |
+
size=1
|
164 |
+
stride=1
|
165 |
+
pad=1
|
166 |
+
activation=leaky
|
167 |
+
|
168 |
+
[convolutional]
|
169 |
+
batch_normalize=1
|
170 |
+
filters=256
|
171 |
+
size=3
|
172 |
+
groups=32
|
173 |
+
stride=1
|
174 |
+
pad=1
|
175 |
+
activation=leaky
|
176 |
+
|
177 |
+
[convolutional]
|
178 |
+
batch_normalize=1
|
179 |
+
filters=512
|
180 |
+
size=1
|
181 |
+
stride=1
|
182 |
+
pad=1
|
183 |
+
activation=linear
|
184 |
+
|
185 |
+
[shortcut]
|
186 |
+
from=-4
|
187 |
+
activation=leaky
|
188 |
+
|
189 |
+
[convolutional]
|
190 |
+
batch_normalize=1
|
191 |
+
filters=256
|
192 |
+
size=1
|
193 |
+
stride=1
|
194 |
+
pad=1
|
195 |
+
activation=leaky
|
196 |
+
|
197 |
+
[convolutional]
|
198 |
+
batch_normalize=1
|
199 |
+
filters=256
|
200 |
+
size=3
|
201 |
+
groups=32
|
202 |
+
stride=1
|
203 |
+
pad=1
|
204 |
+
activation=leaky
|
205 |
+
|
206 |
+
[convolutional]
|
207 |
+
batch_normalize=1
|
208 |
+
filters=512
|
209 |
+
size=1
|
210 |
+
stride=1
|
211 |
+
pad=1
|
212 |
+
activation=linear
|
213 |
+
|
214 |
+
[shortcut]
|
215 |
+
from=-4
|
216 |
+
activation=leaky
|
217 |
+
|
218 |
+
[convolutional]
|
219 |
+
batch_normalize=1
|
220 |
+
filters=256
|
221 |
+
size=1
|
222 |
+
stride=1
|
223 |
+
pad=1
|
224 |
+
activation=leaky
|
225 |
+
|
226 |
+
[convolutional]
|
227 |
+
batch_normalize=1
|
228 |
+
filters=256
|
229 |
+
size=3
|
230 |
+
groups=32
|
231 |
+
stride=1
|
232 |
+
pad=1
|
233 |
+
activation=leaky
|
234 |
+
|
235 |
+
[convolutional]
|
236 |
+
batch_normalize=1
|
237 |
+
filters=512
|
238 |
+
size=1
|
239 |
+
stride=1
|
240 |
+
pad=1
|
241 |
+
activation=linear
|
242 |
+
|
243 |
+
[shortcut]
|
244 |
+
from=-4
|
245 |
+
activation=leaky
|
246 |
+
|
247 |
+
|
248 |
+
# Conv 4
|
249 |
+
[convolutional]
|
250 |
+
batch_normalize=1
|
251 |
+
filters=512
|
252 |
+
size=1
|
253 |
+
stride=1
|
254 |
+
pad=1
|
255 |
+
activation=leaky
|
256 |
+
|
257 |
+
[convolutional]
|
258 |
+
batch_normalize=1
|
259 |
+
filters=512
|
260 |
+
size=3
|
261 |
+
groups=32
|
262 |
+
stride=2
|
263 |
+
pad=1
|
264 |
+
activation=leaky
|
265 |
+
|
266 |
+
[convolutional]
|
267 |
+
batch_normalize=1
|
268 |
+
filters=1024
|
269 |
+
size=1
|
270 |
+
stride=1
|
271 |
+
pad=1
|
272 |
+
activation=linear
|
273 |
+
|
274 |
+
[shortcut]
|
275 |
+
from=-4
|
276 |
+
activation=leaky
|
277 |
+
|
278 |
+
[convolutional]
|
279 |
+
batch_normalize=1
|
280 |
+
filters=512
|
281 |
+
size=1
|
282 |
+
stride=1
|
283 |
+
pad=1
|
284 |
+
activation=leaky
|
285 |
+
|
286 |
+
[convolutional]
|
287 |
+
batch_normalize=1
|
288 |
+
filters=512
|
289 |
+
size=3
|
290 |
+
groups=32
|
291 |
+
stride=1
|
292 |
+
pad=1
|
293 |
+
activation=leaky
|
294 |
+
|
295 |
+
[convolutional]
|
296 |
+
batch_normalize=1
|
297 |
+
filters=1024
|
298 |
+
size=1
|
299 |
+
stride=1
|
300 |
+
pad=1
|
301 |
+
activation=linear
|
302 |
+
|
303 |
+
[shortcut]
|
304 |
+
from=-4
|
305 |
+
activation=leaky
|
306 |
+
|
307 |
+
[convolutional]
|
308 |
+
batch_normalize=1
|
309 |
+
filters=512
|
310 |
+
size=1
|
311 |
+
stride=1
|
312 |
+
pad=1
|
313 |
+
activation=leaky
|
314 |
+
|
315 |
+
[convolutional]
|
316 |
+
batch_normalize=1
|
317 |
+
filters=512
|
318 |
+
size=3
|
319 |
+
groups=32
|
320 |
+
stride=1
|
321 |
+
pad=1
|
322 |
+
activation=leaky
|
323 |
+
|
324 |
+
[convolutional]
|
325 |
+
batch_normalize=1
|
326 |
+
filters=1024
|
327 |
+
size=1
|
328 |
+
stride=1
|
329 |
+
pad=1
|
330 |
+
activation=linear
|
331 |
+
|
332 |
+
[shortcut]
|
333 |
+
from=-4
|
334 |
+
activation=leaky
|
335 |
+
|
336 |
+
[convolutional]
|
337 |
+
batch_normalize=1
|
338 |
+
filters=512
|
339 |
+
size=1
|
340 |
+
stride=1
|
341 |
+
pad=1
|
342 |
+
activation=leaky
|
343 |
+
|
344 |
+
[convolutional]
|
345 |
+
batch_normalize=1
|
346 |
+
filters=512
|
347 |
+
size=3
|
348 |
+
groups=32
|
349 |
+
stride=1
|
350 |
+
pad=1
|
351 |
+
activation=leaky
|
352 |
+
|
353 |
+
[convolutional]
|
354 |
+
batch_normalize=1
|
355 |
+
filters=1024
|
356 |
+
size=1
|
357 |
+
stride=1
|
358 |
+
pad=1
|
359 |
+
activation=linear
|
360 |
+
|
361 |
+
[shortcut]
|
362 |
+
from=-4
|
363 |
+
activation=leaky
|
364 |
+
|
365 |
+
[convolutional]
|
366 |
+
batch_normalize=1
|
367 |
+
filters=512
|
368 |
+
size=1
|
369 |
+
stride=1
|
370 |
+
pad=1
|
371 |
+
activation=leaky
|
372 |
+
|
373 |
+
[convolutional]
|
374 |
+
batch_normalize=1
|
375 |
+
filters=512
|
376 |
+
size=3
|
377 |
+
groups=32
|
378 |
+
stride=1
|
379 |
+
pad=1
|
380 |
+
activation=leaky
|
381 |
+
|
382 |
+
[convolutional]
|
383 |
+
batch_normalize=1
|
384 |
+
filters=1024
|
385 |
+
size=1
|
386 |
+
stride=1
|
387 |
+
pad=1
|
388 |
+
activation=linear
|
389 |
+
|
390 |
+
[shortcut]
|
391 |
+
from=-4
|
392 |
+
activation=leaky
|
393 |
+
|
394 |
+
[convolutional]
|
395 |
+
batch_normalize=1
|
396 |
+
filters=512
|
397 |
+
size=1
|
398 |
+
stride=1
|
399 |
+
pad=1
|
400 |
+
activation=leaky
|
401 |
+
|
402 |
+
[convolutional]
|
403 |
+
batch_normalize=1
|
404 |
+
filters=512
|
405 |
+
size=3
|
406 |
+
groups=32
|
407 |
+
stride=1
|
408 |
+
pad=1
|
409 |
+
activation=leaky
|
410 |
+
|
411 |
+
[convolutional]
|
412 |
+
batch_normalize=1
|
413 |
+
filters=1024
|
414 |
+
size=1
|
415 |
+
stride=1
|
416 |
+
pad=1
|
417 |
+
activation=linear
|
418 |
+
|
419 |
+
[shortcut]
|
420 |
+
from=-4
|
421 |
+
activation=leaky
|
422 |
+
|
423 |
+
#Conv 5
|
424 |
+
[convolutional]
|
425 |
+
batch_normalize=1
|
426 |
+
filters=1024
|
427 |
+
size=1
|
428 |
+
stride=1
|
429 |
+
pad=1
|
430 |
+
activation=leaky
|
431 |
+
|
432 |
+
[convolutional]
|
433 |
+
batch_normalize=1
|
434 |
+
filters=1024
|
435 |
+
size=3
|
436 |
+
groups=32
|
437 |
+
stride=2
|
438 |
+
pad=1
|
439 |
+
activation=leaky
|
440 |
+
|
441 |
+
[convolutional]
|
442 |
+
batch_normalize=1
|
443 |
+
filters=2048
|
444 |
+
size=1
|
445 |
+
stride=1
|
446 |
+
pad=1
|
447 |
+
activation=linear
|
448 |
+
|
449 |
+
[shortcut]
|
450 |
+
from=-4
|
451 |
+
activation=leaky
|
452 |
+
|
453 |
+
[convolutional]
|
454 |
+
batch_normalize=1
|
455 |
+
filters=1024
|
456 |
+
size=1
|
457 |
+
stride=1
|
458 |
+
pad=1
|
459 |
+
activation=leaky
|
460 |
+
|
461 |
+
[convolutional]
|
462 |
+
batch_normalize=1
|
463 |
+
filters=1024
|
464 |
+
size=3
|
465 |
+
groups=32
|
466 |
+
stride=1
|
467 |
+
pad=1
|
468 |
+
activation=leaky
|
469 |
+
|
470 |
+
[convolutional]
|
471 |
+
batch_normalize=1
|
472 |
+
filters=2048
|
473 |
+
size=1
|
474 |
+
stride=1
|
475 |
+
pad=1
|
476 |
+
activation=linear
|
477 |
+
|
478 |
+
[shortcut]
|
479 |
+
from=-4
|
480 |
+
activation=leaky
|
481 |
+
|
482 |
+
[convolutional]
|
483 |
+
batch_normalize=1
|
484 |
+
filters=1024
|
485 |
+
size=1
|
486 |
+
stride=1
|
487 |
+
pad=1
|
488 |
+
activation=leaky
|
489 |
+
|
490 |
+
[convolutional]
|
491 |
+
batch_normalize=1
|
492 |
+
filters=1024
|
493 |
+
size=3
|
494 |
+
groups=32
|
495 |
+
stride=1
|
496 |
+
pad=1
|
497 |
+
activation=leaky
|
498 |
+
|
499 |
+
[convolutional]
|
500 |
+
batch_normalize=1
|
501 |
+
filters=2048
|
502 |
+
size=1
|
503 |
+
stride=1
|
504 |
+
pad=1
|
505 |
+
activation=linear
|
506 |
+
|
507 |
+
[shortcut]
|
508 |
+
from=-4
|
509 |
+
activation=leaky
|
510 |
+
|
511 |
+
[avgpool]
|
512 |
+
|
513 |
+
[convolutional]
|
514 |
+
filters=1000
|
515 |
+
size=1
|
516 |
+
stride=1
|
517 |
+
pad=1
|
518 |
+
activation=linear
|
519 |
+
|
520 |
+
[softmax]
|
521 |
+
groups=1
|
522 |
+
|
523 |
+
|
model/cfg/rnn.cfg
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
subdivisions=1
|
3 |
+
inputs=256
|
4 |
+
batch = 1
|
5 |
+
momentum=0.9
|
6 |
+
decay=0.001
|
7 |
+
max_batches = 2000
|
8 |
+
time_steps=1
|
9 |
+
learning_rate=0.1
|
10 |
+
policy=steps
|
11 |
+
steps=1000,1500
|
12 |
+
scales=.1,.1
|
13 |
+
|
14 |
+
[rnn]
|
15 |
+
batch_normalize=1
|
16 |
+
output = 1024
|
17 |
+
hidden=1024
|
18 |
+
activation=leaky
|
19 |
+
|
20 |
+
[rnn]
|
21 |
+
batch_normalize=1
|
22 |
+
output = 1024
|
23 |
+
hidden=1024
|
24 |
+
activation=leaky
|
25 |
+
|
26 |
+
[rnn]
|
27 |
+
batch_normalize=1
|
28 |
+
output = 1024
|
29 |
+
hidden=1024
|
30 |
+
activation=leaky
|
31 |
+
|
32 |
+
[connected]
|
33 |
+
output=256
|
34 |
+
activation=leaky
|
35 |
+
|
36 |
+
[softmax]
|
37 |
+
|
38 |
+
|
model/cfg/rnn.train.cfg
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
subdivisions=1
|
3 |
+
inputs=256
|
4 |
+
batch = 128
|
5 |
+
momentum=0.9
|
6 |
+
decay=0.001
|
7 |
+
max_batches = 2000
|
8 |
+
time_steps=576
|
9 |
+
learning_rate=0.1
|
10 |
+
policy=steps
|
11 |
+
steps=1000,1500
|
12 |
+
scales=.1,.1
|
13 |
+
|
14 |
+
[rnn]
|
15 |
+
batch_normalize=1
|
16 |
+
output = 1024
|
17 |
+
hidden=1024
|
18 |
+
activation=leaky
|
19 |
+
|
20 |
+
[rnn]
|
21 |
+
batch_normalize=1
|
22 |
+
output = 1024
|
23 |
+
hidden=1024
|
24 |
+
activation=leaky
|
25 |
+
|
26 |
+
[rnn]
|
27 |
+
batch_normalize=1
|
28 |
+
output = 1024
|
29 |
+
hidden=1024
|
30 |
+
activation=leaky
|
31 |
+
|
32 |
+
[connected]
|
33 |
+
output=256
|
34 |
+
activation=leaky
|
35 |
+
|
36 |
+
[softmax]
|
37 |
+
|
38 |
+
|
model/cfg/strided.cfg
ADDED
@@ -0,0 +1,182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=128
|
3 |
+
subdivisions=4
|
4 |
+
height=256
|
5 |
+
width=256
|
6 |
+
channels=3
|
7 |
+
momentum=0.9
|
8 |
+
decay=0.0005
|
9 |
+
|
10 |
+
learning_rate=0.01
|
11 |
+
policy=steps
|
12 |
+
scales=.1,.1,.1
|
13 |
+
steps=200000,300000,400000
|
14 |
+
max_batches=800000
|
15 |
+
|
16 |
+
|
17 |
+
[crop]
|
18 |
+
crop_height=224
|
19 |
+
crop_width=224
|
20 |
+
flip=1
|
21 |
+
angle=0
|
22 |
+
saturation=1
|
23 |
+
exposure=1
|
24 |
+
shift=.2
|
25 |
+
|
26 |
+
[convolutional]
|
27 |
+
filters=64
|
28 |
+
size=7
|
29 |
+
stride=2
|
30 |
+
pad=1
|
31 |
+
activation=ramp
|
32 |
+
|
33 |
+
[convolutional]
|
34 |
+
filters=192
|
35 |
+
size=3
|
36 |
+
stride=2
|
37 |
+
pad=1
|
38 |
+
activation=ramp
|
39 |
+
|
40 |
+
[convolutional]
|
41 |
+
filters=128
|
42 |
+
size=1
|
43 |
+
stride=1
|
44 |
+
pad=1
|
45 |
+
activation=ramp
|
46 |
+
|
47 |
+
[convolutional]
|
48 |
+
filters=256
|
49 |
+
size=3
|
50 |
+
stride=2
|
51 |
+
pad=1
|
52 |
+
activation=ramp
|
53 |
+
|
54 |
+
[convolutional]
|
55 |
+
filters=128
|
56 |
+
size=1
|
57 |
+
stride=1
|
58 |
+
pad=1
|
59 |
+
activation=ramp
|
60 |
+
|
61 |
+
[convolutional]
|
62 |
+
filters=256
|
63 |
+
size=3
|
64 |
+
stride=1
|
65 |
+
pad=1
|
66 |
+
activation=ramp
|
67 |
+
|
68 |
+
[convolutional]
|
69 |
+
filters=128
|
70 |
+
size=1
|
71 |
+
stride=1
|
72 |
+
pad=1
|
73 |
+
activation=ramp
|
74 |
+
|
75 |
+
[convolutional]
|
76 |
+
filters=512
|
77 |
+
size=3
|
78 |
+
stride=2
|
79 |
+
pad=1
|
80 |
+
activation=ramp
|
81 |
+
|
82 |
+
[convolutional]
|
83 |
+
filters=256
|
84 |
+
size=1
|
85 |
+
stride=1
|
86 |
+
pad=1
|
87 |
+
activation=ramp
|
88 |
+
|
89 |
+
[convolutional]
|
90 |
+
filters=512
|
91 |
+
size=3
|
92 |
+
stride=1
|
93 |
+
pad=1
|
94 |
+
activation=ramp
|
95 |
+
|
96 |
+
[convolutional]
|
97 |
+
filters=256
|
98 |
+
size=1
|
99 |
+
stride=1
|
100 |
+
pad=1
|
101 |
+
activation=ramp
|
102 |
+
|
103 |
+
[convolutional]
|
104 |
+
filters=512
|
105 |
+
size=3
|
106 |
+
stride=1
|
107 |
+
pad=1
|
108 |
+
activation=ramp
|
109 |
+
|
110 |
+
[convolutional]
|
111 |
+
filters=256
|
112 |
+
size=1
|
113 |
+
stride=1
|
114 |
+
pad=1
|
115 |
+
activation=ramp
|
116 |
+
|
117 |
+
[convolutional]
|
118 |
+
filters=512
|
119 |
+
size=3
|
120 |
+
stride=1
|
121 |
+
pad=1
|
122 |
+
activation=ramp
|
123 |
+
|
124 |
+
[convolutional]
|
125 |
+
filters=256
|
126 |
+
size=1
|
127 |
+
stride=1
|
128 |
+
pad=1
|
129 |
+
activation=ramp
|
130 |
+
|
131 |
+
[convolutional]
|
132 |
+
filters=512
|
133 |
+
size=3
|
134 |
+
stride=1
|
135 |
+
pad=1
|
136 |
+
activation=ramp
|
137 |
+
|
138 |
+
[convolutional]
|
139 |
+
filters=256
|
140 |
+
size=1
|
141 |
+
stride=1
|
142 |
+
pad=1
|
143 |
+
activation=ramp
|
144 |
+
|
145 |
+
[convolutional]
|
146 |
+
filters=1024
|
147 |
+
size=3
|
148 |
+
stride=2
|
149 |
+
pad=1
|
150 |
+
activation=ramp
|
151 |
+
|
152 |
+
[convolutional]
|
153 |
+
filters=512
|
154 |
+
size=1
|
155 |
+
stride=1
|
156 |
+
pad=1
|
157 |
+
activation=ramp
|
158 |
+
|
159 |
+
[convolutional]
|
160 |
+
filters=1024
|
161 |
+
size=3
|
162 |
+
stride=1
|
163 |
+
pad=1
|
164 |
+
activation=ramp
|
165 |
+
|
166 |
+
[maxpool]
|
167 |
+
size=3
|
168 |
+
stride=2
|
169 |
+
|
170 |
+
[connected]
|
171 |
+
output=4096
|
172 |
+
activation=ramp
|
173 |
+
|
174 |
+
[dropout]
|
175 |
+
probability=0.5
|
176 |
+
|
177 |
+
[connected]
|
178 |
+
output=1000
|
179 |
+
activation=ramp
|
180 |
+
|
181 |
+
[softmax]
|
182 |
+
|
model/cfg/t1.test.cfg
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=1
|
3 |
+
subdivisions=1
|
4 |
+
height=224
|
5 |
+
width=224
|
6 |
+
channels=3
|
7 |
+
momentum=0.9
|
8 |
+
decay=0.0005
|
9 |
+
|
10 |
+
learning_rate=0.0005
|
11 |
+
policy=steps
|
12 |
+
steps=200,400,600,20000,30000
|
13 |
+
scales=2.5,2,2,.1,.1
|
14 |
+
max_batches = 40000
|
15 |
+
|
16 |
+
[convolutional]
|
17 |
+
filters=16
|
18 |
+
size=3
|
19 |
+
stride=1
|
20 |
+
pad=1
|
21 |
+
activation=leaky
|
22 |
+
|
23 |
+
[maxpool]
|
24 |
+
size=2
|
25 |
+
stride=2
|
26 |
+
|
27 |
+
[convolutional]
|
28 |
+
filters=32
|
29 |
+
size=3
|
30 |
+
stride=1
|
31 |
+
pad=1
|
32 |
+
activation=leaky
|
33 |
+
|
34 |
+
[maxpool]
|
35 |
+
size=2
|
36 |
+
stride=2
|
37 |
+
|
38 |
+
[convolutional]
|
39 |
+
filters=64
|
40 |
+
size=3
|
41 |
+
stride=1
|
42 |
+
pad=1
|
43 |
+
activation=leaky
|
44 |
+
|
45 |
+
[maxpool]
|
46 |
+
size=2
|
47 |
+
stride=2
|
48 |
+
|
49 |
+
[convolutional]
|
50 |
+
filters=128
|
51 |
+
size=3
|
52 |
+
stride=1
|
53 |
+
pad=1
|
54 |
+
activation=leaky
|
55 |
+
|
56 |
+
[maxpool]
|
57 |
+
size=2
|
58 |
+
stride=2
|
59 |
+
|
60 |
+
[convolutional]
|
61 |
+
filters=256
|
62 |
+
size=3
|
63 |
+
stride=1
|
64 |
+
pad=1
|
65 |
+
activation=leaky
|
66 |
+
|
67 |
+
[maxpool]
|
68 |
+
size=2
|
69 |
+
stride=2
|
70 |
+
|
71 |
+
[convolutional]
|
72 |
+
filters=512
|
73 |
+
size=3
|
74 |
+
stride=1
|
75 |
+
pad=1
|
76 |
+
activation=leaky
|
77 |
+
|
78 |
+
[convolutional]
|
79 |
+
filters=1024
|
80 |
+
size=3
|
81 |
+
stride=1
|
82 |
+
pad=1
|
83 |
+
activation=leaky
|
84 |
+
|
85 |
+
[convolutional]
|
86 |
+
filters=1024
|
87 |
+
size=3
|
88 |
+
stride=1
|
89 |
+
pad=1
|
90 |
+
activation=leaky
|
91 |
+
|
92 |
+
[convolutional]
|
93 |
+
filters=256
|
94 |
+
size=3
|
95 |
+
stride=1
|
96 |
+
pad=1
|
97 |
+
activation=leaky
|
98 |
+
|
99 |
+
[connected]
|
100 |
+
output= 1470
|
101 |
+
activation=linear
|
102 |
+
|
103 |
+
[detection]
|
104 |
+
classes=20
|
105 |
+
coords=4
|
106 |
+
rescore=1
|
107 |
+
side=7
|
108 |
+
num=2
|
109 |
+
softmax=0
|
110 |
+
sqrt=1
|
111 |
+
jitter=.2
|
112 |
+
|
113 |
+
object_scale=1
|
114 |
+
noobject_scale=.5
|
115 |
+
class_scale=1
|
116 |
+
coord_scale=5
|
117 |
+
|
model/cfg/tiny.cfg
ADDED
@@ -0,0 +1,174 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Train
|
3 |
+
batch=128
|
4 |
+
subdivisions=1
|
5 |
+
# Test
|
6 |
+
# batch=1
|
7 |
+
# subdivisions=1
|
8 |
+
height=224
|
9 |
+
width=224
|
10 |
+
channels=3
|
11 |
+
momentum=0.9
|
12 |
+
decay=0.0005
|
13 |
+
max_crop=320
|
14 |
+
|
15 |
+
learning_rate=0.1
|
16 |
+
policy=poly
|
17 |
+
power=4
|
18 |
+
max_batches=1600000
|
19 |
+
|
20 |
+
angle=7
|
21 |
+
hue=.1
|
22 |
+
saturation=.75
|
23 |
+
exposure=.75
|
24 |
+
aspect=.75
|
25 |
+
|
26 |
+
[convolutional]
|
27 |
+
batch_normalize=1
|
28 |
+
filters=16
|
29 |
+
size=3
|
30 |
+
stride=1
|
31 |
+
pad=1
|
32 |
+
activation=leaky
|
33 |
+
|
34 |
+
[maxpool]
|
35 |
+
size=2
|
36 |
+
stride=2
|
37 |
+
|
38 |
+
[convolutional]
|
39 |
+
batch_normalize=1
|
40 |
+
filters=32
|
41 |
+
size=3
|
42 |
+
stride=1
|
43 |
+
pad=1
|
44 |
+
activation=leaky
|
45 |
+
|
46 |
+
[maxpool]
|
47 |
+
size=2
|
48 |
+
stride=2
|
49 |
+
|
50 |
+
[convolutional]
|
51 |
+
batch_normalize=1
|
52 |
+
filters=16
|
53 |
+
size=1
|
54 |
+
stride=1
|
55 |
+
pad=1
|
56 |
+
activation=leaky
|
57 |
+
|
58 |
+
[convolutional]
|
59 |
+
batch_normalize=1
|
60 |
+
filters=128
|
61 |
+
size=3
|
62 |
+
stride=1
|
63 |
+
pad=1
|
64 |
+
activation=leaky
|
65 |
+
|
66 |
+
[convolutional]
|
67 |
+
batch_normalize=1
|
68 |
+
filters=16
|
69 |
+
size=1
|
70 |
+
stride=1
|
71 |
+
pad=1
|
72 |
+
activation=leaky
|
73 |
+
|
74 |
+
[convolutional]
|
75 |
+
batch_normalize=1
|
76 |
+
filters=128
|
77 |
+
size=3
|
78 |
+
stride=1
|
79 |
+
pad=1
|
80 |
+
activation=leaky
|
81 |
+
|
82 |
+
[maxpool]
|
83 |
+
size=2
|
84 |
+
stride=2
|
85 |
+
|
86 |
+
[convolutional]
|
87 |
+
batch_normalize=1
|
88 |
+
filters=32
|
89 |
+
size=1
|
90 |
+
stride=1
|
91 |
+
pad=1
|
92 |
+
activation=leaky
|
93 |
+
|
94 |
+
[convolutional]
|
95 |
+
batch_normalize=1
|
96 |
+
filters=256
|
97 |
+
size=3
|
98 |
+
stride=1
|
99 |
+
pad=1
|
100 |
+
activation=leaky
|
101 |
+
|
102 |
+
[convolutional]
|
103 |
+
batch_normalize=1
|
104 |
+
filters=32
|
105 |
+
size=1
|
106 |
+
stride=1
|
107 |
+
pad=1
|
108 |
+
activation=leaky
|
109 |
+
|
110 |
+
[convolutional]
|
111 |
+
batch_normalize=1
|
112 |
+
filters=256
|
113 |
+
size=3
|
114 |
+
stride=1
|
115 |
+
pad=1
|
116 |
+
activation=leaky
|
117 |
+
|
118 |
+
[maxpool]
|
119 |
+
size=2
|
120 |
+
stride=2
|
121 |
+
|
122 |
+
[convolutional]
|
123 |
+
batch_normalize=1
|
124 |
+
filters=64
|
125 |
+
size=1
|
126 |
+
stride=1
|
127 |
+
pad=1
|
128 |
+
activation=leaky
|
129 |
+
|
130 |
+
[convolutional]
|
131 |
+
batch_normalize=1
|
132 |
+
filters=512
|
133 |
+
size=3
|
134 |
+
stride=1
|
135 |
+
pad=1
|
136 |
+
activation=leaky
|
137 |
+
|
138 |
+
[convolutional]
|
139 |
+
batch_normalize=1
|
140 |
+
filters=64
|
141 |
+
size=1
|
142 |
+
stride=1
|
143 |
+
pad=1
|
144 |
+
activation=leaky
|
145 |
+
|
146 |
+
[convolutional]
|
147 |
+
batch_normalize=1
|
148 |
+
filters=512
|
149 |
+
size=3
|
150 |
+
stride=1
|
151 |
+
pad=1
|
152 |
+
activation=leaky
|
153 |
+
|
154 |
+
[convolutional]
|
155 |
+
batch_normalize=1
|
156 |
+
filters=128
|
157 |
+
size=1
|
158 |
+
stride=1
|
159 |
+
pad=1
|
160 |
+
activation=leaky
|
161 |
+
|
162 |
+
[convolutional]
|
163 |
+
filters=1000
|
164 |
+
size=1
|
165 |
+
stride=1
|
166 |
+
pad=1
|
167 |
+
activation=linear
|
168 |
+
|
169 |
+
[avgpool]
|
170 |
+
|
171 |
+
[softmax]
|
172 |
+
groups=1
|
173 |
+
|
174 |
+
|
model/cfg/vgg-16.cfg
ADDED
@@ -0,0 +1,157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Training
|
3 |
+
# batch=128
|
4 |
+
# subdivisions=4
|
5 |
+
|
6 |
+
# Testing
|
7 |
+
batch=1
|
8 |
+
subdivisions=1
|
9 |
+
|
10 |
+
height=256
|
11 |
+
width=256
|
12 |
+
channels=3
|
13 |
+
learning_rate=0.00001
|
14 |
+
momentum=0.9
|
15 |
+
decay=0.0005
|
16 |
+
|
17 |
+
[crop]
|
18 |
+
crop_height=224
|
19 |
+
crop_width=224
|
20 |
+
flip=1
|
21 |
+
exposure=1
|
22 |
+
saturation=1
|
23 |
+
angle=0
|
24 |
+
|
25 |
+
[convolutional]
|
26 |
+
filters=64
|
27 |
+
size=3
|
28 |
+
stride=1
|
29 |
+
pad=1
|
30 |
+
activation=relu
|
31 |
+
|
32 |
+
[convolutional]
|
33 |
+
filters=64
|
34 |
+
size=3
|
35 |
+
stride=1
|
36 |
+
pad=1
|
37 |
+
activation=relu
|
38 |
+
|
39 |
+
[maxpool]
|
40 |
+
size=2
|
41 |
+
stride=2
|
42 |
+
|
43 |
+
[convolutional]
|
44 |
+
filters=128
|
45 |
+
size=3
|
46 |
+
stride=1
|
47 |
+
pad=1
|
48 |
+
activation=relu
|
49 |
+
|
50 |
+
[convolutional]
|
51 |
+
filters=128
|
52 |
+
size=3
|
53 |
+
stride=1
|
54 |
+
pad=1
|
55 |
+
activation=relu
|
56 |
+
|
57 |
+
[maxpool]
|
58 |
+
size=2
|
59 |
+
stride=2
|
60 |
+
|
61 |
+
[convolutional]
|
62 |
+
filters=256
|
63 |
+
size=3
|
64 |
+
stride=1
|
65 |
+
pad=1
|
66 |
+
activation=relu
|
67 |
+
|
68 |
+
[convolutional]
|
69 |
+
filters=256
|
70 |
+
size=3
|
71 |
+
stride=1
|
72 |
+
pad=1
|
73 |
+
activation=relu
|
74 |
+
|
75 |
+
[convolutional]
|
76 |
+
filters=256
|
77 |
+
size=3
|
78 |
+
stride=1
|
79 |
+
pad=1
|
80 |
+
activation=relu
|
81 |
+
|
82 |
+
[maxpool]
|
83 |
+
size=2
|
84 |
+
stride=2
|
85 |
+
|
86 |
+
[convolutional]
|
87 |
+
filters=512
|
88 |
+
size=3
|
89 |
+
stride=1
|
90 |
+
pad=1
|
91 |
+
activation=relu
|
92 |
+
|
93 |
+
[convolutional]
|
94 |
+
filters=512
|
95 |
+
size=3
|
96 |
+
stride=1
|
97 |
+
pad=1
|
98 |
+
activation=relu
|
99 |
+
|
100 |
+
[convolutional]
|
101 |
+
filters=512
|
102 |
+
size=3
|
103 |
+
stride=1
|
104 |
+
pad=1
|
105 |
+
activation=relu
|
106 |
+
|
107 |
+
[maxpool]
|
108 |
+
size=2
|
109 |
+
stride=2
|
110 |
+
|
111 |
+
[convolutional]
|
112 |
+
filters=512
|
113 |
+
size=3
|
114 |
+
stride=1
|
115 |
+
pad=1
|
116 |
+
activation=relu
|
117 |
+
|
118 |
+
[convolutional]
|
119 |
+
filters=512
|
120 |
+
size=3
|
121 |
+
stride=1
|
122 |
+
pad=1
|
123 |
+
activation=relu
|
124 |
+
|
125 |
+
[convolutional]
|
126 |
+
filters=512
|
127 |
+
size=3
|
128 |
+
stride=1
|
129 |
+
pad=1
|
130 |
+
activation=relu
|
131 |
+
|
132 |
+
[maxpool]
|
133 |
+
size=2
|
134 |
+
stride=2
|
135 |
+
|
136 |
+
[connected]
|
137 |
+
output=4096
|
138 |
+
activation=relu
|
139 |
+
|
140 |
+
[dropout]
|
141 |
+
probability=.5
|
142 |
+
|
143 |
+
[connected]
|
144 |
+
output=4096
|
145 |
+
activation=relu
|
146 |
+
|
147 |
+
[dropout]
|
148 |
+
probability=.5
|
149 |
+
|
150 |
+
[connected]
|
151 |
+
output=1000
|
152 |
+
activation=linear
|
153 |
+
|
154 |
+
[softmax]
|
155 |
+
groups=1
|
156 |
+
|
157 |
+
|
model/cfg/vgg-conv.cfg
ADDED
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=1
|
3 |
+
subdivisions=1
|
4 |
+
width=224
|
5 |
+
height=224
|
6 |
+
channels=3
|
7 |
+
learning_rate=0.00001
|
8 |
+
momentum=0.9
|
9 |
+
decay=0.0005
|
10 |
+
|
11 |
+
[convolutional]
|
12 |
+
filters=64
|
13 |
+
size=3
|
14 |
+
stride=1
|
15 |
+
pad=1
|
16 |
+
activation=relu
|
17 |
+
|
18 |
+
[convolutional]
|
19 |
+
filters=64
|
20 |
+
size=3
|
21 |
+
stride=1
|
22 |
+
pad=1
|
23 |
+
activation=relu
|
24 |
+
|
25 |
+
[maxpool]
|
26 |
+
size=2
|
27 |
+
stride=2
|
28 |
+
|
29 |
+
[convolutional]
|
30 |
+
filters=128
|
31 |
+
size=3
|
32 |
+
stride=1
|
33 |
+
pad=1
|
34 |
+
activation=relu
|
35 |
+
|
36 |
+
[convolutional]
|
37 |
+
filters=128
|
38 |
+
size=3
|
39 |
+
stride=1
|
40 |
+
pad=1
|
41 |
+
activation=relu
|
42 |
+
|
43 |
+
[maxpool]
|
44 |
+
size=2
|
45 |
+
stride=2
|
46 |
+
|
47 |
+
[convolutional]
|
48 |
+
filters=256
|
49 |
+
size=3
|
50 |
+
stride=1
|
51 |
+
pad=1
|
52 |
+
activation=relu
|
53 |
+
|
54 |
+
[convolutional]
|
55 |
+
filters=256
|
56 |
+
size=3
|
57 |
+
stride=1
|
58 |
+
pad=1
|
59 |
+
activation=relu
|
60 |
+
|
61 |
+
[convolutional]
|
62 |
+
filters=256
|
63 |
+
size=3
|
64 |
+
stride=1
|
65 |
+
pad=1
|
66 |
+
activation=relu
|
67 |
+
|
68 |
+
[maxpool]
|
69 |
+
size=2
|
70 |
+
stride=2
|
71 |
+
|
72 |
+
[convolutional]
|
73 |
+
filters=512
|
74 |
+
size=3
|
75 |
+
stride=1
|
76 |
+
pad=1
|
77 |
+
activation=relu
|
78 |
+
|
79 |
+
[convolutional]
|
80 |
+
filters=512
|
81 |
+
size=3
|
82 |
+
stride=1
|
83 |
+
pad=1
|
84 |
+
activation=relu
|
85 |
+
|
86 |
+
[convolutional]
|
87 |
+
filters=512
|
88 |
+
size=3
|
89 |
+
stride=1
|
90 |
+
pad=1
|
91 |
+
activation=relu
|
92 |
+
|
93 |
+
[maxpool]
|
94 |
+
size=2
|
95 |
+
stride=2
|
96 |
+
|
97 |
+
[convolutional]
|
98 |
+
filters=512
|
99 |
+
size=3
|
100 |
+
stride=1
|
101 |
+
pad=1
|
102 |
+
activation=relu
|
103 |
+
|
104 |
+
[convolutional]
|
105 |
+
filters=512
|
106 |
+
size=3
|
107 |
+
stride=1
|
108 |
+
pad=1
|
109 |
+
activation=relu
|
110 |
+
|
111 |
+
[convolutional]
|
112 |
+
filters=512
|
113 |
+
size=3
|
114 |
+
stride=1
|
115 |
+
pad=1
|
116 |
+
activation=relu
|
117 |
+
|
118 |
+
[maxpool]
|
119 |
+
size=2
|
120 |
+
stride=2
|
121 |
+
|
model/cfg/voc.data
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
classes= 20
|
2 |
+
train = /home/pjreddie/data/voc/train.txt
|
3 |
+
valid = /home/pjreddie/data/voc/2007_test.txt
|
4 |
+
names = data/voc.names
|
5 |
+
backup = backup
|
6 |
+
|
model/cfg/writing.cfg
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
batch=128
|
3 |
+
subdivisions=2
|
4 |
+
height=256
|
5 |
+
width=256
|
6 |
+
channels=3
|
7 |
+
learning_rate=0.00000001
|
8 |
+
momentum=0.9
|
9 |
+
decay=0.0005
|
10 |
+
seen=0
|
11 |
+
|
12 |
+
[convolutional]
|
13 |
+
filters=32
|
14 |
+
size=3
|
15 |
+
stride=1
|
16 |
+
pad=1
|
17 |
+
activation=leaky
|
18 |
+
|
19 |
+
[convolutional]
|
20 |
+
filters=32
|
21 |
+
size=3
|
22 |
+
stride=1
|
23 |
+
pad=1
|
24 |
+
activation=leaky
|
25 |
+
|
26 |
+
[convolutional]
|
27 |
+
filters=32
|
28 |
+
size=3
|
29 |
+
stride=1
|
30 |
+
pad=1
|
31 |
+
activation=leaky
|
32 |
+
|
33 |
+
[convolutional]
|
34 |
+
filters=1
|
35 |
+
size=3
|
36 |
+
stride=1
|
37 |
+
pad=1
|
38 |
+
activation=logistic
|
39 |
+
|
40 |
+
[cost]
|
41 |
+
|
model/cfg/yolo9000.cfg
ADDED
@@ -0,0 +1,218 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Testing
|
3 |
+
batch=1
|
4 |
+
subdivisions=1
|
5 |
+
# Training
|
6 |
+
# batch=64
|
7 |
+
# subdivisions=8
|
8 |
+
batch=1
|
9 |
+
subdivisions=1
|
10 |
+
height=544
|
11 |
+
width=544
|
12 |
+
channels=3
|
13 |
+
momentum=0.9
|
14 |
+
decay=0.0005
|
15 |
+
|
16 |
+
learning_rate=0.001
|
17 |
+
burn_in=1000
|
18 |
+
max_batches = 500200
|
19 |
+
policy=steps
|
20 |
+
steps=400000,450000
|
21 |
+
scales=.1,.1
|
22 |
+
|
23 |
+
hue=.1
|
24 |
+
saturation=.75
|
25 |
+
exposure=.75
|
26 |
+
|
27 |
+
[convolutional]
|
28 |
+
batch_normalize=1
|
29 |
+
filters=32
|
30 |
+
size=3
|
31 |
+
stride=1
|
32 |
+
pad=1
|
33 |
+
activation=leaky
|
34 |
+
|
35 |
+
[maxpool]
|
36 |
+
size=2
|
37 |
+
stride=2
|
38 |
+
|
39 |
+
[convolutional]
|
40 |
+
batch_normalize=1
|
41 |
+
filters=64
|
42 |
+
size=3
|
43 |
+
stride=1
|
44 |
+
pad=1
|
45 |
+
activation=leaky
|
46 |
+
|
47 |
+
[maxpool]
|
48 |
+
size=2
|
49 |
+
stride=2
|
50 |
+
|
51 |
+
[convolutional]
|
52 |
+
batch_normalize=1
|
53 |
+
filters=128
|
54 |
+
size=3
|
55 |
+
stride=1
|
56 |
+
pad=1
|
57 |
+
activation=leaky
|
58 |
+
|
59 |
+
[convolutional]
|
60 |
+
batch_normalize=1
|
61 |
+
filters=64
|
62 |
+
size=1
|
63 |
+
stride=1
|
64 |
+
pad=1
|
65 |
+
activation=leaky
|
66 |
+
|
67 |
+
[convolutional]
|
68 |
+
batch_normalize=1
|
69 |
+
filters=128
|
70 |
+
size=3
|
71 |
+
stride=1
|
72 |
+
pad=1
|
73 |
+
activation=leaky
|
74 |
+
|
75 |
+
[maxpool]
|
76 |
+
size=2
|
77 |
+
stride=2
|
78 |
+
|
79 |
+
[convolutional]
|
80 |
+
batch_normalize=1
|
81 |
+
filters=256
|
82 |
+
size=3
|
83 |
+
stride=1
|
84 |
+
pad=1
|
85 |
+
activation=leaky
|
86 |
+
|
87 |
+
[convolutional]
|
88 |
+
batch_normalize=1
|
89 |
+
filters=128
|
90 |
+
size=1
|
91 |
+
stride=1
|
92 |
+
pad=1
|
93 |
+
activation=leaky
|
94 |
+
|
95 |
+
[convolutional]
|
96 |
+
batch_normalize=1
|
97 |
+
filters=256
|
98 |
+
size=3
|
99 |
+
stride=1
|
100 |
+
pad=1
|
101 |
+
activation=leaky
|
102 |
+
|
103 |
+
[maxpool]
|
104 |
+
size=2
|
105 |
+
stride=2
|
106 |
+
|
107 |
+
[convolutional]
|
108 |
+
batch_normalize=1
|
109 |
+
filters=512
|
110 |
+
size=3
|
111 |
+
stride=1
|
112 |
+
pad=1
|
113 |
+
activation=leaky
|
114 |
+
|
115 |
+
[convolutional]
|
116 |
+
batch_normalize=1
|
117 |
+
filters=256
|
118 |
+
size=1
|
119 |
+
stride=1
|
120 |
+
pad=1
|
121 |
+
activation=leaky
|
122 |
+
|
123 |
+
[convolutional]
|
124 |
+
batch_normalize=1
|
125 |
+
filters=512
|
126 |
+
size=3
|
127 |
+
stride=1
|
128 |
+
pad=1
|
129 |
+
activation=leaky
|
130 |
+
|
131 |
+
[convolutional]
|
132 |
+
batch_normalize=1
|
133 |
+
filters=256
|
134 |
+
size=1
|
135 |
+
stride=1
|
136 |
+
pad=1
|
137 |
+
activation=leaky
|
138 |
+
|
139 |
+
[convolutional]
|
140 |
+
batch_normalize=1
|
141 |
+
filters=512
|
142 |
+
size=3
|
143 |
+
stride=1
|
144 |
+
pad=1
|
145 |
+
activation=leaky
|
146 |
+
|
147 |
+
[maxpool]
|
148 |
+
size=2
|
149 |
+
stride=2
|
150 |
+
|
151 |
+
[convolutional]
|
152 |
+
batch_normalize=1
|
153 |
+
filters=1024
|
154 |
+
size=3
|
155 |
+
stride=1
|
156 |
+
pad=1
|
157 |
+
activation=leaky
|
158 |
+
|
159 |
+
[convolutional]
|
160 |
+
batch_normalize=1
|
161 |
+
filters=512
|
162 |
+
size=1
|
163 |
+
stride=1
|
164 |
+
pad=1
|
165 |
+
activation=leaky
|
166 |
+
|
167 |
+
[convolutional]
|
168 |
+
batch_normalize=1
|
169 |
+
filters=1024
|
170 |
+
size=3
|
171 |
+
stride=1
|
172 |
+
pad=1
|
173 |
+
activation=leaky
|
174 |
+
|
175 |
+
[convolutional]
|
176 |
+
batch_normalize=1
|
177 |
+
filters=512
|
178 |
+
size=1
|
179 |
+
stride=1
|
180 |
+
pad=1
|
181 |
+
activation=leaky
|
182 |
+
|
183 |
+
[convolutional]
|
184 |
+
batch_normalize=1
|
185 |
+
filters=1024
|
186 |
+
size=3
|
187 |
+
stride=1
|
188 |
+
pad=1
|
189 |
+
activation=leaky
|
190 |
+
|
191 |
+
[convolutional]
|
192 |
+
filters=28269
|
193 |
+
size=1
|
194 |
+
stride=1
|
195 |
+
pad=1
|
196 |
+
activation=linear
|
197 |
+
|
198 |
+
[region]
|
199 |
+
anchors = 0.77871, 1.14074, 3.00525, 4.31277, 9.22725, 9.61974
|
200 |
+
bias_match=1
|
201 |
+
classes=9418
|
202 |
+
coords=4
|
203 |
+
num=3
|
204 |
+
softmax=1
|
205 |
+
jitter=.2
|
206 |
+
rescore=1
|
207 |
+
|
208 |
+
object_scale=5
|
209 |
+
noobject_scale=1
|
210 |
+
class_scale=1
|
211 |
+
coord_scale=1
|
212 |
+
|
213 |
+
thresh = .6
|
214 |
+
absolute=1
|
215 |
+
random=1
|
216 |
+
|
217 |
+
tree=data/9k.tree
|
218 |
+
map = data/coco9k.map
|
model/cfg/yolov1-tiny.cfg
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Testing
|
3 |
+
batch=1
|
4 |
+
subdivisions=1
|
5 |
+
# Training
|
6 |
+
# batch=64
|
7 |
+
# subdivisions=8
|
8 |
+
height=448
|
9 |
+
width=448
|
10 |
+
channels=3
|
11 |
+
momentum=0.9
|
12 |
+
decay=0.0005
|
13 |
+
|
14 |
+
saturation=.75
|
15 |
+
exposure=.75
|
16 |
+
hue = .1
|
17 |
+
|
18 |
+
learning_rate=0.0005
|
19 |
+
policy=steps
|
20 |
+
steps=200,400,600,800,20000,30000
|
21 |
+
scales=2.5,2,2,2,.1,.1
|
22 |
+
max_batches = 40000
|
23 |
+
|
24 |
+
[convolutional]
|
25 |
+
batch_normalize=1
|
26 |
+
filters=16
|
27 |
+
size=3
|
28 |
+
stride=1
|
29 |
+
pad=1
|
30 |
+
activation=leaky
|
31 |
+
|
32 |
+
[maxpool]
|
33 |
+
size=2
|
34 |
+
stride=2
|
35 |
+
|
36 |
+
[convolutional]
|
37 |
+
batch_normalize=1
|
38 |
+
filters=32
|
39 |
+
size=3
|
40 |
+
stride=1
|
41 |
+
pad=1
|
42 |
+
activation=leaky
|
43 |
+
|
44 |
+
[maxpool]
|
45 |
+
size=2
|
46 |
+
stride=2
|
47 |
+
|
48 |
+
[convolutional]
|
49 |
+
batch_normalize=1
|
50 |
+
filters=64
|
51 |
+
size=3
|
52 |
+
stride=1
|
53 |
+
pad=1
|
54 |
+
activation=leaky
|
55 |
+
|
56 |
+
[maxpool]
|
57 |
+
size=2
|
58 |
+
stride=2
|
59 |
+
|
60 |
+
[convolutional]
|
61 |
+
batch_normalize=1
|
62 |
+
filters=128
|
63 |
+
size=3
|
64 |
+
stride=1
|
65 |
+
pad=1
|
66 |
+
activation=leaky
|
67 |
+
|
68 |
+
[maxpool]
|
69 |
+
size=2
|
70 |
+
stride=2
|
71 |
+
|
72 |
+
[convolutional]
|
73 |
+
batch_normalize=1
|
74 |
+
filters=256
|
75 |
+
size=3
|
76 |
+
stride=1
|
77 |
+
pad=1
|
78 |
+
activation=leaky
|
79 |
+
|
80 |
+
[maxpool]
|
81 |
+
size=2
|
82 |
+
stride=2
|
83 |
+
|
84 |
+
[convolutional]
|
85 |
+
batch_normalize=1
|
86 |
+
filters=512
|
87 |
+
size=3
|
88 |
+
stride=1
|
89 |
+
pad=1
|
90 |
+
activation=leaky
|
91 |
+
|
92 |
+
[maxpool]
|
93 |
+
size=2
|
94 |
+
stride=2
|
95 |
+
|
96 |
+
[convolutional]
|
97 |
+
batch_normalize=1
|
98 |
+
size=3
|
99 |
+
stride=1
|
100 |
+
pad=1
|
101 |
+
filters=1024
|
102 |
+
activation=leaky
|
103 |
+
|
104 |
+
[convolutional]
|
105 |
+
batch_normalize=1
|
106 |
+
size=3
|
107 |
+
stride=1
|
108 |
+
pad=1
|
109 |
+
filters=256
|
110 |
+
activation=leaky
|
111 |
+
|
112 |
+
[connected]
|
113 |
+
output= 1470
|
114 |
+
activation=linear
|
115 |
+
|
116 |
+
[detection]
|
117 |
+
classes=20
|
118 |
+
coords=4
|
119 |
+
rescore=1
|
120 |
+
side=7
|
121 |
+
num=2
|
122 |
+
softmax=0
|
123 |
+
sqrt=1
|
124 |
+
jitter=.2
|
125 |
+
|
126 |
+
object_scale=1
|
127 |
+
noobject_scale=.5
|
128 |
+
class_scale=1
|
129 |
+
coord_scale=5
|
130 |
+
|
model/cfg/yolov1.cfg
ADDED
@@ -0,0 +1,261 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Testing
|
3 |
+
batch=1
|
4 |
+
subdivisions=1
|
5 |
+
# Training
|
6 |
+
# batch=64
|
7 |
+
# subdivisions=8
|
8 |
+
height=448
|
9 |
+
width=448
|
10 |
+
channels=3
|
11 |
+
momentum=0.9
|
12 |
+
decay=0.0005
|
13 |
+
saturation=1.5
|
14 |
+
exposure=1.5
|
15 |
+
hue=.1
|
16 |
+
|
17 |
+
learning_rate=0.0005
|
18 |
+
policy=steps
|
19 |
+
steps=200,400,600,20000,30000
|
20 |
+
scales=2.5,2,2,.1,.1
|
21 |
+
max_batches = 40000
|
22 |
+
|
23 |
+
[convolutional]
|
24 |
+
batch_normalize=1
|
25 |
+
filters=64
|
26 |
+
size=7
|
27 |
+
stride=2
|
28 |
+
pad=1
|
29 |
+
activation=leaky
|
30 |
+
|
31 |
+
[maxpool]
|
32 |
+
size=2
|
33 |
+
stride=2
|
34 |
+
|
35 |
+
[convolutional]
|
36 |
+
batch_normalize=1
|
37 |
+
filters=192
|
38 |
+
size=3
|
39 |
+
stride=1
|
40 |
+
pad=1
|
41 |
+
activation=leaky
|
42 |
+
|
43 |
+
[maxpool]
|
44 |
+
size=2
|
45 |
+
stride=2
|
46 |
+
|
47 |
+
[convolutional]
|
48 |
+
batch_normalize=1
|
49 |
+
filters=128
|
50 |
+
size=1
|
51 |
+
stride=1
|
52 |
+
pad=1
|
53 |
+
activation=leaky
|
54 |
+
|
55 |
+
[convolutional]
|
56 |
+
batch_normalize=1
|
57 |
+
filters=256
|
58 |
+
size=3
|
59 |
+
stride=1
|
60 |
+
pad=1
|
61 |
+
activation=leaky
|
62 |
+
|
63 |
+
[convolutional]
|
64 |
+
batch_normalize=1
|
65 |
+
filters=256
|
66 |
+
size=1
|
67 |
+
stride=1
|
68 |
+
pad=1
|
69 |
+
activation=leaky
|
70 |
+
|
71 |
+
[convolutional]
|
72 |
+
batch_normalize=1
|
73 |
+
filters=512
|
74 |
+
size=3
|
75 |
+
stride=1
|
76 |
+
pad=1
|
77 |
+
activation=leaky
|
78 |
+
|
79 |
+
[maxpool]
|
80 |
+
size=2
|
81 |
+
stride=2
|
82 |
+
|
83 |
+
[convolutional]
|
84 |
+
batch_normalize=1
|
85 |
+
filters=256
|
86 |
+
size=1
|
87 |
+
stride=1
|
88 |
+
pad=1
|
89 |
+
activation=leaky
|
90 |
+
|
91 |
+
[convolutional]
|
92 |
+
batch_normalize=1
|
93 |
+
filters=512
|
94 |
+
size=3
|
95 |
+
stride=1
|
96 |
+
pad=1
|
97 |
+
activation=leaky
|
98 |
+
|
99 |
+
[convolutional]
|
100 |
+
batch_normalize=1
|
101 |
+
filters=256
|
102 |
+
size=1
|
103 |
+
stride=1
|
104 |
+
pad=1
|
105 |
+
activation=leaky
|
106 |
+
|
107 |
+
[convolutional]
|
108 |
+
batch_normalize=1
|
109 |
+
filters=512
|
110 |
+
size=3
|
111 |
+
stride=1
|
112 |
+
pad=1
|
113 |
+
activation=leaky
|
114 |
+
|
115 |
+
[convolutional]
|
116 |
+
batch_normalize=1
|
117 |
+
filters=256
|
118 |
+
size=1
|
119 |
+
stride=1
|
120 |
+
pad=1
|
121 |
+
activation=leaky
|
122 |
+
|
123 |
+
[convolutional]
|
124 |
+
batch_normalize=1
|
125 |
+
filters=512
|
126 |
+
size=3
|
127 |
+
stride=1
|
128 |
+
pad=1
|
129 |
+
activation=leaky
|
130 |
+
|
131 |
+
[convolutional]
|
132 |
+
batch_normalize=1
|
133 |
+
filters=256
|
134 |
+
size=1
|
135 |
+
stride=1
|
136 |
+
pad=1
|
137 |
+
activation=leaky
|
138 |
+
|
139 |
+
[convolutional]
|
140 |
+
batch_normalize=1
|
141 |
+
filters=512
|
142 |
+
size=3
|
143 |
+
stride=1
|
144 |
+
pad=1
|
145 |
+
activation=leaky
|
146 |
+
|
147 |
+
[convolutional]
|
148 |
+
batch_normalize=1
|
149 |
+
filters=512
|
150 |
+
size=1
|
151 |
+
stride=1
|
152 |
+
pad=1
|
153 |
+
activation=leaky
|
154 |
+
|
155 |
+
[convolutional]
|
156 |
+
batch_normalize=1
|
157 |
+
filters=1024
|
158 |
+
size=3
|
159 |
+
stride=1
|
160 |
+
pad=1
|
161 |
+
activation=leaky
|
162 |
+
|
163 |
+
[maxpool]
|
164 |
+
size=2
|
165 |
+
stride=2
|
166 |
+
|
167 |
+
[convolutional]
|
168 |
+
batch_normalize=1
|
169 |
+
filters=512
|
170 |
+
size=1
|
171 |
+
stride=1
|
172 |
+
pad=1
|
173 |
+
activation=leaky
|
174 |
+
|
175 |
+
[convolutional]
|
176 |
+
batch_normalize=1
|
177 |
+
filters=1024
|
178 |
+
size=3
|
179 |
+
stride=1
|
180 |
+
pad=1
|
181 |
+
activation=leaky
|
182 |
+
|
183 |
+
[convolutional]
|
184 |
+
batch_normalize=1
|
185 |
+
filters=512
|
186 |
+
size=1
|
187 |
+
stride=1
|
188 |
+
pad=1
|
189 |
+
activation=leaky
|
190 |
+
|
191 |
+
[convolutional]
|
192 |
+
batch_normalize=1
|
193 |
+
filters=1024
|
194 |
+
size=3
|
195 |
+
stride=1
|
196 |
+
pad=1
|
197 |
+
activation=leaky
|
198 |
+
|
199 |
+
#######
|
200 |
+
|
201 |
+
[convolutional]
|
202 |
+
batch_normalize=1
|
203 |
+
size=3
|
204 |
+
stride=1
|
205 |
+
pad=1
|
206 |
+
filters=1024
|
207 |
+
activation=leaky
|
208 |
+
|
209 |
+
[convolutional]
|
210 |
+
batch_normalize=1
|
211 |
+
size=3
|
212 |
+
stride=2
|
213 |
+
pad=1
|
214 |
+
filters=1024
|
215 |
+
activation=leaky
|
216 |
+
|
217 |
+
[convolutional]
|
218 |
+
batch_normalize=1
|
219 |
+
size=3
|
220 |
+
stride=1
|
221 |
+
pad=1
|
222 |
+
filters=1024
|
223 |
+
activation=leaky
|
224 |
+
|
225 |
+
[convolutional]
|
226 |
+
batch_normalize=1
|
227 |
+
size=3
|
228 |
+
stride=1
|
229 |
+
pad=1
|
230 |
+
filters=1024
|
231 |
+
activation=leaky
|
232 |
+
|
233 |
+
[local]
|
234 |
+
size=3
|
235 |
+
stride=1
|
236 |
+
pad=1
|
237 |
+
filters=256
|
238 |
+
activation=leaky
|
239 |
+
|
240 |
+
[dropout]
|
241 |
+
probability=.5
|
242 |
+
|
243 |
+
[connected]
|
244 |
+
output= 1715
|
245 |
+
activation=linear
|
246 |
+
|
247 |
+
[detection]
|
248 |
+
classes=20
|
249 |
+
coords=4
|
250 |
+
rescore=1
|
251 |
+
side=7
|
252 |
+
num=3
|
253 |
+
softmax=0
|
254 |
+
sqrt=1
|
255 |
+
jitter=.2
|
256 |
+
|
257 |
+
object_scale=1
|
258 |
+
noobject_scale=.5
|
259 |
+
class_scale=1
|
260 |
+
coord_scale=5
|
261 |
+
|
model/cfg/yolov2-tiny-voc.cfg
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Testing
|
3 |
+
batch=1
|
4 |
+
subdivisions=1
|
5 |
+
# Training
|
6 |
+
# batch=64
|
7 |
+
# subdivisions=2
|
8 |
+
width=416
|
9 |
+
height=416
|
10 |
+
channels=3
|
11 |
+
momentum=0.9
|
12 |
+
decay=0.0005
|
13 |
+
angle=0
|
14 |
+
saturation = 1.5
|
15 |
+
exposure = 1.5
|
16 |
+
hue=.1
|
17 |
+
|
18 |
+
learning_rate=0.001
|
19 |
+
max_batches = 40200
|
20 |
+
policy=steps
|
21 |
+
steps=-1,100,20000,30000
|
22 |
+
scales=.1,10,.1,.1
|
23 |
+
|
24 |
+
[convolutional]
|
25 |
+
batch_normalize=1
|
26 |
+
filters=16
|
27 |
+
size=3
|
28 |
+
stride=1
|
29 |
+
pad=1
|
30 |
+
activation=leaky
|
31 |
+
|
32 |
+
[maxpool]
|
33 |
+
size=2
|
34 |
+
stride=2
|
35 |
+
|
36 |
+
[convolutional]
|
37 |
+
batch_normalize=1
|
38 |
+
filters=32
|
39 |
+
size=3
|
40 |
+
stride=1
|
41 |
+
pad=1
|
42 |
+
activation=leaky
|
43 |
+
|
44 |
+
[maxpool]
|
45 |
+
size=2
|
46 |
+
stride=2
|
47 |
+
|
48 |
+
[convolutional]
|
49 |
+
batch_normalize=1
|
50 |
+
filters=64
|
51 |
+
size=3
|
52 |
+
stride=1
|
53 |
+
pad=1
|
54 |
+
activation=leaky
|
55 |
+
|
56 |
+
[maxpool]
|
57 |
+
size=2
|
58 |
+
stride=2
|
59 |
+
|
60 |
+
[convolutional]
|
61 |
+
batch_normalize=1
|
62 |
+
filters=128
|
63 |
+
size=3
|
64 |
+
stride=1
|
65 |
+
pad=1
|
66 |
+
activation=leaky
|
67 |
+
|
68 |
+
[maxpool]
|
69 |
+
size=2
|
70 |
+
stride=2
|
71 |
+
|
72 |
+
[convolutional]
|
73 |
+
batch_normalize=1
|
74 |
+
filters=256
|
75 |
+
size=3
|
76 |
+
stride=1
|
77 |
+
pad=1
|
78 |
+
activation=leaky
|
79 |
+
|
80 |
+
[maxpool]
|
81 |
+
size=2
|
82 |
+
stride=2
|
83 |
+
|
84 |
+
[convolutional]
|
85 |
+
batch_normalize=1
|
86 |
+
filters=512
|
87 |
+
size=3
|
88 |
+
stride=1
|
89 |
+
pad=1
|
90 |
+
activation=leaky
|
91 |
+
|
92 |
+
[maxpool]
|
93 |
+
size=2
|
94 |
+
stride=1
|
95 |
+
|
96 |
+
[convolutional]
|
97 |
+
batch_normalize=1
|
98 |
+
filters=1024
|
99 |
+
size=3
|
100 |
+
stride=1
|
101 |
+
pad=1
|
102 |
+
activation=leaky
|
103 |
+
|
104 |
+
###########
|
105 |
+
|
106 |
+
[convolutional]
|
107 |
+
batch_normalize=1
|
108 |
+
size=3
|
109 |
+
stride=1
|
110 |
+
pad=1
|
111 |
+
filters=1024
|
112 |
+
activation=leaky
|
113 |
+
|
114 |
+
[convolutional]
|
115 |
+
size=1
|
116 |
+
stride=1
|
117 |
+
pad=1
|
118 |
+
filters=125
|
119 |
+
activation=linear
|
120 |
+
|
121 |
+
[region]
|
122 |
+
anchors = 1.08,1.19, 3.42,4.41, 6.63,11.38, 9.42,5.11, 16.62,10.52
|
123 |
+
bias_match=1
|
124 |
+
classes=20
|
125 |
+
coords=4
|
126 |
+
num=5
|
127 |
+
softmax=1
|
128 |
+
jitter=.2
|
129 |
+
rescore=1
|
130 |
+
|
131 |
+
object_scale=5
|
132 |
+
noobject_scale=1
|
133 |
+
class_scale=1
|
134 |
+
coord_scale=1
|
135 |
+
|
136 |
+
absolute=1
|
137 |
+
thresh = .6
|
138 |
+
random=1
|
model/cfg/yolov2-tiny.cfg
ADDED
@@ -0,0 +1,139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Testing
|
3 |
+
batch=1
|
4 |
+
subdivisions=1
|
5 |
+
# Training
|
6 |
+
# batch=64
|
7 |
+
# subdivisions=2
|
8 |
+
width=416
|
9 |
+
height=416
|
10 |
+
channels=3
|
11 |
+
momentum=0.9
|
12 |
+
decay=0.0005
|
13 |
+
angle=0
|
14 |
+
saturation = 1.5
|
15 |
+
exposure = 1.5
|
16 |
+
hue=.1
|
17 |
+
|
18 |
+
learning_rate=0.001
|
19 |
+
burn_in=1000
|
20 |
+
max_batches = 500200
|
21 |
+
policy=steps
|
22 |
+
steps=400000,450000
|
23 |
+
scales=.1,.1
|
24 |
+
|
25 |
+
[convolutional]
|
26 |
+
batch_normalize=1
|
27 |
+
filters=16
|
28 |
+
size=3
|
29 |
+
stride=1
|
30 |
+
pad=1
|
31 |
+
activation=leaky
|
32 |
+
|
33 |
+
[maxpool]
|
34 |
+
size=2
|
35 |
+
stride=2
|
36 |
+
|
37 |
+
[convolutional]
|
38 |
+
batch_normalize=1
|
39 |
+
filters=32
|
40 |
+
size=3
|
41 |
+
stride=1
|
42 |
+
pad=1
|
43 |
+
activation=leaky
|
44 |
+
|
45 |
+
[maxpool]
|
46 |
+
size=2
|
47 |
+
stride=2
|
48 |
+
|
49 |
+
[convolutional]
|
50 |
+
batch_normalize=1
|
51 |
+
filters=64
|
52 |
+
size=3
|
53 |
+
stride=1
|
54 |
+
pad=1
|
55 |
+
activation=leaky
|
56 |
+
|
57 |
+
[maxpool]
|
58 |
+
size=2
|
59 |
+
stride=2
|
60 |
+
|
61 |
+
[convolutional]
|
62 |
+
batch_normalize=1
|
63 |
+
filters=128
|
64 |
+
size=3
|
65 |
+
stride=1
|
66 |
+
pad=1
|
67 |
+
activation=leaky
|
68 |
+
|
69 |
+
[maxpool]
|
70 |
+
size=2
|
71 |
+
stride=2
|
72 |
+
|
73 |
+
[convolutional]
|
74 |
+
batch_normalize=1
|
75 |
+
filters=256
|
76 |
+
size=3
|
77 |
+
stride=1
|
78 |
+
pad=1
|
79 |
+
activation=leaky
|
80 |
+
|
81 |
+
[maxpool]
|
82 |
+
size=2
|
83 |
+
stride=2
|
84 |
+
|
85 |
+
[convolutional]
|
86 |
+
batch_normalize=1
|
87 |
+
filters=512
|
88 |
+
size=3
|
89 |
+
stride=1
|
90 |
+
pad=1
|
91 |
+
activation=leaky
|
92 |
+
|
93 |
+
[maxpool]
|
94 |
+
size=2
|
95 |
+
stride=1
|
96 |
+
|
97 |
+
[convolutional]
|
98 |
+
batch_normalize=1
|
99 |
+
filters=1024
|
100 |
+
size=3
|
101 |
+
stride=1
|
102 |
+
pad=1
|
103 |
+
activation=leaky
|
104 |
+
|
105 |
+
###########
|
106 |
+
|
107 |
+
[convolutional]
|
108 |
+
batch_normalize=1
|
109 |
+
size=3
|
110 |
+
stride=1
|
111 |
+
pad=1
|
112 |
+
filters=512
|
113 |
+
activation=leaky
|
114 |
+
|
115 |
+
[convolutional]
|
116 |
+
size=1
|
117 |
+
stride=1
|
118 |
+
pad=1
|
119 |
+
filters=425
|
120 |
+
activation=linear
|
121 |
+
|
122 |
+
[region]
|
123 |
+
anchors = 0.57273, 0.677385, 1.87446, 2.06253, 3.33843, 5.47434, 7.88282, 3.52778, 9.77052, 9.16828
|
124 |
+
bias_match=1
|
125 |
+
classes=80
|
126 |
+
coords=4
|
127 |
+
num=5
|
128 |
+
softmax=1
|
129 |
+
jitter=.2
|
130 |
+
rescore=0
|
131 |
+
|
132 |
+
object_scale=5
|
133 |
+
noobject_scale=1
|
134 |
+
class_scale=1
|
135 |
+
coord_scale=1
|
136 |
+
|
137 |
+
absolute=1
|
138 |
+
thresh = .6
|
139 |
+
random=1
|
model/cfg/yolov2-voc.cfg
ADDED
@@ -0,0 +1,258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Testing
|
3 |
+
batch=1
|
4 |
+
subdivisions=1
|
5 |
+
# Training
|
6 |
+
# batch=64
|
7 |
+
# subdivisions=8
|
8 |
+
height=416
|
9 |
+
width=416
|
10 |
+
channels=3
|
11 |
+
momentum=0.9
|
12 |
+
decay=0.0005
|
13 |
+
angle=0
|
14 |
+
saturation = 1.5
|
15 |
+
exposure = 1.5
|
16 |
+
hue=.1
|
17 |
+
|
18 |
+
learning_rate=0.001
|
19 |
+
burn_in=1000
|
20 |
+
max_batches = 80200
|
21 |
+
policy=steps
|
22 |
+
steps=40000,60000
|
23 |
+
scales=.1,.1
|
24 |
+
|
25 |
+
[convolutional]
|
26 |
+
batch_normalize=1
|
27 |
+
filters=32
|
28 |
+
size=3
|
29 |
+
stride=1
|
30 |
+
pad=1
|
31 |
+
activation=leaky
|
32 |
+
|
33 |
+
[maxpool]
|
34 |
+
size=2
|
35 |
+
stride=2
|
36 |
+
|
37 |
+
[convolutional]
|
38 |
+
batch_normalize=1
|
39 |
+
filters=64
|
40 |
+
size=3
|
41 |
+
stride=1
|
42 |
+
pad=1
|
43 |
+
activation=leaky
|
44 |
+
|
45 |
+
[maxpool]
|
46 |
+
size=2
|
47 |
+
stride=2
|
48 |
+
|
49 |
+
[convolutional]
|
50 |
+
batch_normalize=1
|
51 |
+
filters=128
|
52 |
+
size=3
|
53 |
+
stride=1
|
54 |
+
pad=1
|
55 |
+
activation=leaky
|
56 |
+
|
57 |
+
[convolutional]
|
58 |
+
batch_normalize=1
|
59 |
+
filters=64
|
60 |
+
size=1
|
61 |
+
stride=1
|
62 |
+
pad=1
|
63 |
+
activation=leaky
|
64 |
+
|
65 |
+
[convolutional]
|
66 |
+
batch_normalize=1
|
67 |
+
filters=128
|
68 |
+
size=3
|
69 |
+
stride=1
|
70 |
+
pad=1
|
71 |
+
activation=leaky
|
72 |
+
|
73 |
+
[maxpool]
|
74 |
+
size=2
|
75 |
+
stride=2
|
76 |
+
|
77 |
+
[convolutional]
|
78 |
+
batch_normalize=1
|
79 |
+
filters=256
|
80 |
+
size=3
|
81 |
+
stride=1
|
82 |
+
pad=1
|
83 |
+
activation=leaky
|
84 |
+
|
85 |
+
[convolutional]
|
86 |
+
batch_normalize=1
|
87 |
+
filters=128
|
88 |
+
size=1
|
89 |
+
stride=1
|
90 |
+
pad=1
|
91 |
+
activation=leaky
|
92 |
+
|
93 |
+
[convolutional]
|
94 |
+
batch_normalize=1
|
95 |
+
filters=256
|
96 |
+
size=3
|
97 |
+
stride=1
|
98 |
+
pad=1
|
99 |
+
activation=leaky
|
100 |
+
|
101 |
+
[maxpool]
|
102 |
+
size=2
|
103 |
+
stride=2
|
104 |
+
|
105 |
+
[convolutional]
|
106 |
+
batch_normalize=1
|
107 |
+
filters=512
|
108 |
+
size=3
|
109 |
+
stride=1
|
110 |
+
pad=1
|
111 |
+
activation=leaky
|
112 |
+
|
113 |
+
[convolutional]
|
114 |
+
batch_normalize=1
|
115 |
+
filters=256
|
116 |
+
size=1
|
117 |
+
stride=1
|
118 |
+
pad=1
|
119 |
+
activation=leaky
|
120 |
+
|
121 |
+
[convolutional]
|
122 |
+
batch_normalize=1
|
123 |
+
filters=512
|
124 |
+
size=3
|
125 |
+
stride=1
|
126 |
+
pad=1
|
127 |
+
activation=leaky
|
128 |
+
|
129 |
+
[convolutional]
|
130 |
+
batch_normalize=1
|
131 |
+
filters=256
|
132 |
+
size=1
|
133 |
+
stride=1
|
134 |
+
pad=1
|
135 |
+
activation=leaky
|
136 |
+
|
137 |
+
[convolutional]
|
138 |
+
batch_normalize=1
|
139 |
+
filters=512
|
140 |
+
size=3
|
141 |
+
stride=1
|
142 |
+
pad=1
|
143 |
+
activation=leaky
|
144 |
+
|
145 |
+
[maxpool]
|
146 |
+
size=2
|
147 |
+
stride=2
|
148 |
+
|
149 |
+
[convolutional]
|
150 |
+
batch_normalize=1
|
151 |
+
filters=1024
|
152 |
+
size=3
|
153 |
+
stride=1
|
154 |
+
pad=1
|
155 |
+
activation=leaky
|
156 |
+
|
157 |
+
[convolutional]
|
158 |
+
batch_normalize=1
|
159 |
+
filters=512
|
160 |
+
size=1
|
161 |
+
stride=1
|
162 |
+
pad=1
|
163 |
+
activation=leaky
|
164 |
+
|
165 |
+
[convolutional]
|
166 |
+
batch_normalize=1
|
167 |
+
filters=1024
|
168 |
+
size=3
|
169 |
+
stride=1
|
170 |
+
pad=1
|
171 |
+
activation=leaky
|
172 |
+
|
173 |
+
[convolutional]
|
174 |
+
batch_normalize=1
|
175 |
+
filters=512
|
176 |
+
size=1
|
177 |
+
stride=1
|
178 |
+
pad=1
|
179 |
+
activation=leaky
|
180 |
+
|
181 |
+
[convolutional]
|
182 |
+
batch_normalize=1
|
183 |
+
filters=1024
|
184 |
+
size=3
|
185 |
+
stride=1
|
186 |
+
pad=1
|
187 |
+
activation=leaky
|
188 |
+
|
189 |
+
|
190 |
+
#######
|
191 |
+
|
192 |
+
[convolutional]
|
193 |
+
batch_normalize=1
|
194 |
+
size=3
|
195 |
+
stride=1
|
196 |
+
pad=1
|
197 |
+
filters=1024
|
198 |
+
activation=leaky
|
199 |
+
|
200 |
+
[convolutional]
|
201 |
+
batch_normalize=1
|
202 |
+
size=3
|
203 |
+
stride=1
|
204 |
+
pad=1
|
205 |
+
filters=1024
|
206 |
+
activation=leaky
|
207 |
+
|
208 |
+
[route]
|
209 |
+
layers=-9
|
210 |
+
|
211 |
+
[convolutional]
|
212 |
+
batch_normalize=1
|
213 |
+
size=1
|
214 |
+
stride=1
|
215 |
+
pad=1
|
216 |
+
filters=64
|
217 |
+
activation=leaky
|
218 |
+
|
219 |
+
[reorg]
|
220 |
+
stride=2
|
221 |
+
|
222 |
+
[route]
|
223 |
+
layers=-1,-4
|
224 |
+
|
225 |
+
[convolutional]
|
226 |
+
batch_normalize=1
|
227 |
+
size=3
|
228 |
+
stride=1
|
229 |
+
pad=1
|
230 |
+
filters=1024
|
231 |
+
activation=leaky
|
232 |
+
|
233 |
+
[convolutional]
|
234 |
+
size=1
|
235 |
+
stride=1
|
236 |
+
pad=1
|
237 |
+
filters=125
|
238 |
+
activation=linear
|
239 |
+
|
240 |
+
|
241 |
+
[region]
|
242 |
+
anchors = 1.3221, 1.73145, 3.19275, 4.00944, 5.05587, 8.09892, 9.47112, 4.84053, 11.2364, 10.0071
|
243 |
+
bias_match=1
|
244 |
+
classes=20
|
245 |
+
coords=4
|
246 |
+
num=5
|
247 |
+
softmax=1
|
248 |
+
jitter=.3
|
249 |
+
rescore=1
|
250 |
+
|
251 |
+
object_scale=5
|
252 |
+
noobject_scale=1
|
253 |
+
class_scale=1
|
254 |
+
coord_scale=1
|
255 |
+
|
256 |
+
absolute=1
|
257 |
+
thresh = .6
|
258 |
+
random=1
|
model/cfg/yolov2.cfg
ADDED
@@ -0,0 +1,258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Testing
|
3 |
+
batch=1
|
4 |
+
subdivisions=1
|
5 |
+
# Training
|
6 |
+
# batch=64
|
7 |
+
# subdivisions=8
|
8 |
+
width=608
|
9 |
+
height=608
|
10 |
+
channels=3
|
11 |
+
momentum=0.9
|
12 |
+
decay=0.0005
|
13 |
+
angle=0
|
14 |
+
saturation = 1.5
|
15 |
+
exposure = 1.5
|
16 |
+
hue=.1
|
17 |
+
|
18 |
+
learning_rate=0.001
|
19 |
+
burn_in=1000
|
20 |
+
max_batches = 500200
|
21 |
+
policy=steps
|
22 |
+
steps=400000,450000
|
23 |
+
scales=.1,.1
|
24 |
+
|
25 |
+
[convolutional]
|
26 |
+
batch_normalize=1
|
27 |
+
filters=32
|
28 |
+
size=3
|
29 |
+
stride=1
|
30 |
+
pad=1
|
31 |
+
activation=leaky
|
32 |
+
|
33 |
+
[maxpool]
|
34 |
+
size=2
|
35 |
+
stride=2
|
36 |
+
|
37 |
+
[convolutional]
|
38 |
+
batch_normalize=1
|
39 |
+
filters=64
|
40 |
+
size=3
|
41 |
+
stride=1
|
42 |
+
pad=1
|
43 |
+
activation=leaky
|
44 |
+
|
45 |
+
[maxpool]
|
46 |
+
size=2
|
47 |
+
stride=2
|
48 |
+
|
49 |
+
[convolutional]
|
50 |
+
batch_normalize=1
|
51 |
+
filters=128
|
52 |
+
size=3
|
53 |
+
stride=1
|
54 |
+
pad=1
|
55 |
+
activation=leaky
|
56 |
+
|
57 |
+
[convolutional]
|
58 |
+
batch_normalize=1
|
59 |
+
filters=64
|
60 |
+
size=1
|
61 |
+
stride=1
|
62 |
+
pad=1
|
63 |
+
activation=leaky
|
64 |
+
|
65 |
+
[convolutional]
|
66 |
+
batch_normalize=1
|
67 |
+
filters=128
|
68 |
+
size=3
|
69 |
+
stride=1
|
70 |
+
pad=1
|
71 |
+
activation=leaky
|
72 |
+
|
73 |
+
[maxpool]
|
74 |
+
size=2
|
75 |
+
stride=2
|
76 |
+
|
77 |
+
[convolutional]
|
78 |
+
batch_normalize=1
|
79 |
+
filters=256
|
80 |
+
size=3
|
81 |
+
stride=1
|
82 |
+
pad=1
|
83 |
+
activation=leaky
|
84 |
+
|
85 |
+
[convolutional]
|
86 |
+
batch_normalize=1
|
87 |
+
filters=128
|
88 |
+
size=1
|
89 |
+
stride=1
|
90 |
+
pad=1
|
91 |
+
activation=leaky
|
92 |
+
|
93 |
+
[convolutional]
|
94 |
+
batch_normalize=1
|
95 |
+
filters=256
|
96 |
+
size=3
|
97 |
+
stride=1
|
98 |
+
pad=1
|
99 |
+
activation=leaky
|
100 |
+
|
101 |
+
[maxpool]
|
102 |
+
size=2
|
103 |
+
stride=2
|
104 |
+
|
105 |
+
[convolutional]
|
106 |
+
batch_normalize=1
|
107 |
+
filters=512
|
108 |
+
size=3
|
109 |
+
stride=1
|
110 |
+
pad=1
|
111 |
+
activation=leaky
|
112 |
+
|
113 |
+
[convolutional]
|
114 |
+
batch_normalize=1
|
115 |
+
filters=256
|
116 |
+
size=1
|
117 |
+
stride=1
|
118 |
+
pad=1
|
119 |
+
activation=leaky
|
120 |
+
|
121 |
+
[convolutional]
|
122 |
+
batch_normalize=1
|
123 |
+
filters=512
|
124 |
+
size=3
|
125 |
+
stride=1
|
126 |
+
pad=1
|
127 |
+
activation=leaky
|
128 |
+
|
129 |
+
[convolutional]
|
130 |
+
batch_normalize=1
|
131 |
+
filters=256
|
132 |
+
size=1
|
133 |
+
stride=1
|
134 |
+
pad=1
|
135 |
+
activation=leaky
|
136 |
+
|
137 |
+
[convolutional]
|
138 |
+
batch_normalize=1
|
139 |
+
filters=512
|
140 |
+
size=3
|
141 |
+
stride=1
|
142 |
+
pad=1
|
143 |
+
activation=leaky
|
144 |
+
|
145 |
+
[maxpool]
|
146 |
+
size=2
|
147 |
+
stride=2
|
148 |
+
|
149 |
+
[convolutional]
|
150 |
+
batch_normalize=1
|
151 |
+
filters=1024
|
152 |
+
size=3
|
153 |
+
stride=1
|
154 |
+
pad=1
|
155 |
+
activation=leaky
|
156 |
+
|
157 |
+
[convolutional]
|
158 |
+
batch_normalize=1
|
159 |
+
filters=512
|
160 |
+
size=1
|
161 |
+
stride=1
|
162 |
+
pad=1
|
163 |
+
activation=leaky
|
164 |
+
|
165 |
+
[convolutional]
|
166 |
+
batch_normalize=1
|
167 |
+
filters=1024
|
168 |
+
size=3
|
169 |
+
stride=1
|
170 |
+
pad=1
|
171 |
+
activation=leaky
|
172 |
+
|
173 |
+
[convolutional]
|
174 |
+
batch_normalize=1
|
175 |
+
filters=512
|
176 |
+
size=1
|
177 |
+
stride=1
|
178 |
+
pad=1
|
179 |
+
activation=leaky
|
180 |
+
|
181 |
+
[convolutional]
|
182 |
+
batch_normalize=1
|
183 |
+
filters=1024
|
184 |
+
size=3
|
185 |
+
stride=1
|
186 |
+
pad=1
|
187 |
+
activation=leaky
|
188 |
+
|
189 |
+
|
190 |
+
#######
|
191 |
+
|
192 |
+
[convolutional]
|
193 |
+
batch_normalize=1
|
194 |
+
size=3
|
195 |
+
stride=1
|
196 |
+
pad=1
|
197 |
+
filters=1024
|
198 |
+
activation=leaky
|
199 |
+
|
200 |
+
[convolutional]
|
201 |
+
batch_normalize=1
|
202 |
+
size=3
|
203 |
+
stride=1
|
204 |
+
pad=1
|
205 |
+
filters=1024
|
206 |
+
activation=leaky
|
207 |
+
|
208 |
+
[route]
|
209 |
+
layers=-9
|
210 |
+
|
211 |
+
[convolutional]
|
212 |
+
batch_normalize=1
|
213 |
+
size=1
|
214 |
+
stride=1
|
215 |
+
pad=1
|
216 |
+
filters=64
|
217 |
+
activation=leaky
|
218 |
+
|
219 |
+
[reorg]
|
220 |
+
stride=2
|
221 |
+
|
222 |
+
[route]
|
223 |
+
layers=-1,-4
|
224 |
+
|
225 |
+
[convolutional]
|
226 |
+
batch_normalize=1
|
227 |
+
size=3
|
228 |
+
stride=1
|
229 |
+
pad=1
|
230 |
+
filters=1024
|
231 |
+
activation=leaky
|
232 |
+
|
233 |
+
[convolutional]
|
234 |
+
size=1
|
235 |
+
stride=1
|
236 |
+
pad=1
|
237 |
+
filters=425
|
238 |
+
activation=linear
|
239 |
+
|
240 |
+
|
241 |
+
[region]
|
242 |
+
anchors = 0.57273, 0.677385, 1.87446, 2.06253, 3.33843, 5.47434, 7.88282, 3.52778, 9.77052, 9.16828
|
243 |
+
bias_match=1
|
244 |
+
classes=80
|
245 |
+
coords=4
|
246 |
+
num=5
|
247 |
+
softmax=1
|
248 |
+
jitter=.3
|
249 |
+
rescore=1
|
250 |
+
|
251 |
+
object_scale=5
|
252 |
+
noobject_scale=1
|
253 |
+
class_scale=1
|
254 |
+
coord_scale=1
|
255 |
+
|
256 |
+
absolute=1
|
257 |
+
thresh = .6
|
258 |
+
random=1
|
model/cfg/yolov3-openimages.cfg
ADDED
@@ -0,0 +1,789 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Testing
|
3 |
+
batch=1
|
4 |
+
subdivisions=1
|
5 |
+
# Training
|
6 |
+
batch=64
|
7 |
+
subdivisions=16
|
8 |
+
width=608
|
9 |
+
height=608
|
10 |
+
channels=3
|
11 |
+
momentum=0.9
|
12 |
+
decay=0.0005
|
13 |
+
angle=0
|
14 |
+
saturation = 1.5
|
15 |
+
exposure = 1.5
|
16 |
+
hue=.1
|
17 |
+
|
18 |
+
learning_rate=0.001
|
19 |
+
burn_in=5000
|
20 |
+
max_batches = 500200
|
21 |
+
policy=steps
|
22 |
+
steps=400000,450000
|
23 |
+
scales=.1,.1
|
24 |
+
|
25 |
+
[convolutional]
|
26 |
+
batch_normalize=1
|
27 |
+
filters=32
|
28 |
+
size=3
|
29 |
+
stride=1
|
30 |
+
pad=1
|
31 |
+
activation=leaky
|
32 |
+
|
33 |
+
# Downsample
|
34 |
+
|
35 |
+
[convolutional]
|
36 |
+
batch_normalize=1
|
37 |
+
filters=64
|
38 |
+
size=3
|
39 |
+
stride=2
|
40 |
+
pad=1
|
41 |
+
activation=leaky
|
42 |
+
|
43 |
+
[convolutional]
|
44 |
+
batch_normalize=1
|
45 |
+
filters=32
|
46 |
+
size=1
|
47 |
+
stride=1
|
48 |
+
pad=1
|
49 |
+
activation=leaky
|
50 |
+
|
51 |
+
[convolutional]
|
52 |
+
batch_normalize=1
|
53 |
+
filters=64
|
54 |
+
size=3
|
55 |
+
stride=1
|
56 |
+
pad=1
|
57 |
+
activation=leaky
|
58 |
+
|
59 |
+
[shortcut]
|
60 |
+
from=-3
|
61 |
+
activation=linear
|
62 |
+
|
63 |
+
# Downsample
|
64 |
+
|
65 |
+
[convolutional]
|
66 |
+
batch_normalize=1
|
67 |
+
filters=128
|
68 |
+
size=3
|
69 |
+
stride=2
|
70 |
+
pad=1
|
71 |
+
activation=leaky
|
72 |
+
|
73 |
+
[convolutional]
|
74 |
+
batch_normalize=1
|
75 |
+
filters=64
|
76 |
+
size=1
|
77 |
+
stride=1
|
78 |
+
pad=1
|
79 |
+
activation=leaky
|
80 |
+
|
81 |
+
[convolutional]
|
82 |
+
batch_normalize=1
|
83 |
+
filters=128
|
84 |
+
size=3
|
85 |
+
stride=1
|
86 |
+
pad=1
|
87 |
+
activation=leaky
|
88 |
+
|
89 |
+
[shortcut]
|
90 |
+
from=-3
|
91 |
+
activation=linear
|
92 |
+
|
93 |
+
[convolutional]
|
94 |
+
batch_normalize=1
|
95 |
+
filters=64
|
96 |
+
size=1
|
97 |
+
stride=1
|
98 |
+
pad=1
|
99 |
+
activation=leaky
|
100 |
+
|
101 |
+
[convolutional]
|
102 |
+
batch_normalize=1
|
103 |
+
filters=128
|
104 |
+
size=3
|
105 |
+
stride=1
|
106 |
+
pad=1
|
107 |
+
activation=leaky
|
108 |
+
|
109 |
+
[shortcut]
|
110 |
+
from=-3
|
111 |
+
activation=linear
|
112 |
+
|
113 |
+
# Downsample
|
114 |
+
|
115 |
+
[convolutional]
|
116 |
+
batch_normalize=1
|
117 |
+
filters=256
|
118 |
+
size=3
|
119 |
+
stride=2
|
120 |
+
pad=1
|
121 |
+
activation=leaky
|
122 |
+
|
123 |
+
[convolutional]
|
124 |
+
batch_normalize=1
|
125 |
+
filters=128
|
126 |
+
size=1
|
127 |
+
stride=1
|
128 |
+
pad=1
|
129 |
+
activation=leaky
|
130 |
+
|
131 |
+
[convolutional]
|
132 |
+
batch_normalize=1
|
133 |
+
filters=256
|
134 |
+
size=3
|
135 |
+
stride=1
|
136 |
+
pad=1
|
137 |
+
activation=leaky
|
138 |
+
|
139 |
+
[shortcut]
|
140 |
+
from=-3
|
141 |
+
activation=linear
|
142 |
+
|
143 |
+
[convolutional]
|
144 |
+
batch_normalize=1
|
145 |
+
filters=128
|
146 |
+
size=1
|
147 |
+
stride=1
|
148 |
+
pad=1
|
149 |
+
activation=leaky
|
150 |
+
|
151 |
+
[convolutional]
|
152 |
+
batch_normalize=1
|
153 |
+
filters=256
|
154 |
+
size=3
|
155 |
+
stride=1
|
156 |
+
pad=1
|
157 |
+
activation=leaky
|
158 |
+
|
159 |
+
[shortcut]
|
160 |
+
from=-3
|
161 |
+
activation=linear
|
162 |
+
|
163 |
+
[convolutional]
|
164 |
+
batch_normalize=1
|
165 |
+
filters=128
|
166 |
+
size=1
|
167 |
+
stride=1
|
168 |
+
pad=1
|
169 |
+
activation=leaky
|
170 |
+
|
171 |
+
[convolutional]
|
172 |
+
batch_normalize=1
|
173 |
+
filters=256
|
174 |
+
size=3
|
175 |
+
stride=1
|
176 |
+
pad=1
|
177 |
+
activation=leaky
|
178 |
+
|
179 |
+
[shortcut]
|
180 |
+
from=-3
|
181 |
+
activation=linear
|
182 |
+
|
183 |
+
[convolutional]
|
184 |
+
batch_normalize=1
|
185 |
+
filters=128
|
186 |
+
size=1
|
187 |
+
stride=1
|
188 |
+
pad=1
|
189 |
+
activation=leaky
|
190 |
+
|
191 |
+
[convolutional]
|
192 |
+
batch_normalize=1
|
193 |
+
filters=256
|
194 |
+
size=3
|
195 |
+
stride=1
|
196 |
+
pad=1
|
197 |
+
activation=leaky
|
198 |
+
|
199 |
+
[shortcut]
|
200 |
+
from=-3
|
201 |
+
activation=linear
|
202 |
+
|
203 |
+
|
204 |
+
[convolutional]
|
205 |
+
batch_normalize=1
|
206 |
+
filters=128
|
207 |
+
size=1
|
208 |
+
stride=1
|
209 |
+
pad=1
|
210 |
+
activation=leaky
|
211 |
+
|
212 |
+
[convolutional]
|
213 |
+
batch_normalize=1
|
214 |
+
filters=256
|
215 |
+
size=3
|
216 |
+
stride=1
|
217 |
+
pad=1
|
218 |
+
activation=leaky
|
219 |
+
|
220 |
+
[shortcut]
|
221 |
+
from=-3
|
222 |
+
activation=linear
|
223 |
+
|
224 |
+
[convolutional]
|
225 |
+
batch_normalize=1
|
226 |
+
filters=128
|
227 |
+
size=1
|
228 |
+
stride=1
|
229 |
+
pad=1
|
230 |
+
activation=leaky
|
231 |
+
|
232 |
+
[convolutional]
|
233 |
+
batch_normalize=1
|
234 |
+
filters=256
|
235 |
+
size=3
|
236 |
+
stride=1
|
237 |
+
pad=1
|
238 |
+
activation=leaky
|
239 |
+
|
240 |
+
[shortcut]
|
241 |
+
from=-3
|
242 |
+
activation=linear
|
243 |
+
|
244 |
+
[convolutional]
|
245 |
+
batch_normalize=1
|
246 |
+
filters=128
|
247 |
+
size=1
|
248 |
+
stride=1
|
249 |
+
pad=1
|
250 |
+
activation=leaky
|
251 |
+
|
252 |
+
[convolutional]
|
253 |
+
batch_normalize=1
|
254 |
+
filters=256
|
255 |
+
size=3
|
256 |
+
stride=1
|
257 |
+
pad=1
|
258 |
+
activation=leaky
|
259 |
+
|
260 |
+
[shortcut]
|
261 |
+
from=-3
|
262 |
+
activation=linear
|
263 |
+
|
264 |
+
[convolutional]
|
265 |
+
batch_normalize=1
|
266 |
+
filters=128
|
267 |
+
size=1
|
268 |
+
stride=1
|
269 |
+
pad=1
|
270 |
+
activation=leaky
|
271 |
+
|
272 |
+
[convolutional]
|
273 |
+
batch_normalize=1
|
274 |
+
filters=256
|
275 |
+
size=3
|
276 |
+
stride=1
|
277 |
+
pad=1
|
278 |
+
activation=leaky
|
279 |
+
|
280 |
+
[shortcut]
|
281 |
+
from=-3
|
282 |
+
activation=linear
|
283 |
+
|
284 |
+
# Downsample
|
285 |
+
|
286 |
+
[convolutional]
|
287 |
+
batch_normalize=1
|
288 |
+
filters=512
|
289 |
+
size=3
|
290 |
+
stride=2
|
291 |
+
pad=1
|
292 |
+
activation=leaky
|
293 |
+
|
294 |
+
[convolutional]
|
295 |
+
batch_normalize=1
|
296 |
+
filters=256
|
297 |
+
size=1
|
298 |
+
stride=1
|
299 |
+
pad=1
|
300 |
+
activation=leaky
|
301 |
+
|
302 |
+
[convolutional]
|
303 |
+
batch_normalize=1
|
304 |
+
filters=512
|
305 |
+
size=3
|
306 |
+
stride=1
|
307 |
+
pad=1
|
308 |
+
activation=leaky
|
309 |
+
|
310 |
+
[shortcut]
|
311 |
+
from=-3
|
312 |
+
activation=linear
|
313 |
+
|
314 |
+
|
315 |
+
[convolutional]
|
316 |
+
batch_normalize=1
|
317 |
+
filters=256
|
318 |
+
size=1
|
319 |
+
stride=1
|
320 |
+
pad=1
|
321 |
+
activation=leaky
|
322 |
+
|
323 |
+
[convolutional]
|
324 |
+
batch_normalize=1
|
325 |
+
filters=512
|
326 |
+
size=3
|
327 |
+
stride=1
|
328 |
+
pad=1
|
329 |
+
activation=leaky
|
330 |
+
|
331 |
+
[shortcut]
|
332 |
+
from=-3
|
333 |
+
activation=linear
|
334 |
+
|
335 |
+
|
336 |
+
[convolutional]
|
337 |
+
batch_normalize=1
|
338 |
+
filters=256
|
339 |
+
size=1
|
340 |
+
stride=1
|
341 |
+
pad=1
|
342 |
+
activation=leaky
|
343 |
+
|
344 |
+
[convolutional]
|
345 |
+
batch_normalize=1
|
346 |
+
filters=512
|
347 |
+
size=3
|
348 |
+
stride=1
|
349 |
+
pad=1
|
350 |
+
activation=leaky
|
351 |
+
|
352 |
+
[shortcut]
|
353 |
+
from=-3
|
354 |
+
activation=linear
|
355 |
+
|
356 |
+
|
357 |
+
[convolutional]
|
358 |
+
batch_normalize=1
|
359 |
+
filters=256
|
360 |
+
size=1
|
361 |
+
stride=1
|
362 |
+
pad=1
|
363 |
+
activation=leaky
|
364 |
+
|
365 |
+
[convolutional]
|
366 |
+
batch_normalize=1
|
367 |
+
filters=512
|
368 |
+
size=3
|
369 |
+
stride=1
|
370 |
+
pad=1
|
371 |
+
activation=leaky
|
372 |
+
|
373 |
+
[shortcut]
|
374 |
+
from=-3
|
375 |
+
activation=linear
|
376 |
+
|
377 |
+
[convolutional]
|
378 |
+
batch_normalize=1
|
379 |
+
filters=256
|
380 |
+
size=1
|
381 |
+
stride=1
|
382 |
+
pad=1
|
383 |
+
activation=leaky
|
384 |
+
|
385 |
+
[convolutional]
|
386 |
+
batch_normalize=1
|
387 |
+
filters=512
|
388 |
+
size=3
|
389 |
+
stride=1
|
390 |
+
pad=1
|
391 |
+
activation=leaky
|
392 |
+
|
393 |
+
[shortcut]
|
394 |
+
from=-3
|
395 |
+
activation=linear
|
396 |
+
|
397 |
+
|
398 |
+
[convolutional]
|
399 |
+
batch_normalize=1
|
400 |
+
filters=256
|
401 |
+
size=1
|
402 |
+
stride=1
|
403 |
+
pad=1
|
404 |
+
activation=leaky
|
405 |
+
|
406 |
+
[convolutional]
|
407 |
+
batch_normalize=1
|
408 |
+
filters=512
|
409 |
+
size=3
|
410 |
+
stride=1
|
411 |
+
pad=1
|
412 |
+
activation=leaky
|
413 |
+
|
414 |
+
[shortcut]
|
415 |
+
from=-3
|
416 |
+
activation=linear
|
417 |
+
|
418 |
+
|
419 |
+
[convolutional]
|
420 |
+
batch_normalize=1
|
421 |
+
filters=256
|
422 |
+
size=1
|
423 |
+
stride=1
|
424 |
+
pad=1
|
425 |
+
activation=leaky
|
426 |
+
|
427 |
+
[convolutional]
|
428 |
+
batch_normalize=1
|
429 |
+
filters=512
|
430 |
+
size=3
|
431 |
+
stride=1
|
432 |
+
pad=1
|
433 |
+
activation=leaky
|
434 |
+
|
435 |
+
[shortcut]
|
436 |
+
from=-3
|
437 |
+
activation=linear
|
438 |
+
|
439 |
+
[convolutional]
|
440 |
+
batch_normalize=1
|
441 |
+
filters=256
|
442 |
+
size=1
|
443 |
+
stride=1
|
444 |
+
pad=1
|
445 |
+
activation=leaky
|
446 |
+
|
447 |
+
[convolutional]
|
448 |
+
batch_normalize=1
|
449 |
+
filters=512
|
450 |
+
size=3
|
451 |
+
stride=1
|
452 |
+
pad=1
|
453 |
+
activation=leaky
|
454 |
+
|
455 |
+
[shortcut]
|
456 |
+
from=-3
|
457 |
+
activation=linear
|
458 |
+
|
459 |
+
# Downsample
|
460 |
+
|
461 |
+
[convolutional]
|
462 |
+
batch_normalize=1
|
463 |
+
filters=1024
|
464 |
+
size=3
|
465 |
+
stride=2
|
466 |
+
pad=1
|
467 |
+
activation=leaky
|
468 |
+
|
469 |
+
[convolutional]
|
470 |
+
batch_normalize=1
|
471 |
+
filters=512
|
472 |
+
size=1
|
473 |
+
stride=1
|
474 |
+
pad=1
|
475 |
+
activation=leaky
|
476 |
+
|
477 |
+
[convolutional]
|
478 |
+
batch_normalize=1
|
479 |
+
filters=1024
|
480 |
+
size=3
|
481 |
+
stride=1
|
482 |
+
pad=1
|
483 |
+
activation=leaky
|
484 |
+
|
485 |
+
[shortcut]
|
486 |
+
from=-3
|
487 |
+
activation=linear
|
488 |
+
|
489 |
+
[convolutional]
|
490 |
+
batch_normalize=1
|
491 |
+
filters=512
|
492 |
+
size=1
|
493 |
+
stride=1
|
494 |
+
pad=1
|
495 |
+
activation=leaky
|
496 |
+
|
497 |
+
[convolutional]
|
498 |
+
batch_normalize=1
|
499 |
+
filters=1024
|
500 |
+
size=3
|
501 |
+
stride=1
|
502 |
+
pad=1
|
503 |
+
activation=leaky
|
504 |
+
|
505 |
+
[shortcut]
|
506 |
+
from=-3
|
507 |
+
activation=linear
|
508 |
+
|
509 |
+
[convolutional]
|
510 |
+
batch_normalize=1
|
511 |
+
filters=512
|
512 |
+
size=1
|
513 |
+
stride=1
|
514 |
+
pad=1
|
515 |
+
activation=leaky
|
516 |
+
|
517 |
+
[convolutional]
|
518 |
+
batch_normalize=1
|
519 |
+
filters=1024
|
520 |
+
size=3
|
521 |
+
stride=1
|
522 |
+
pad=1
|
523 |
+
activation=leaky
|
524 |
+
|
525 |
+
[shortcut]
|
526 |
+
from=-3
|
527 |
+
activation=linear
|
528 |
+
|
529 |
+
[convolutional]
|
530 |
+
batch_normalize=1
|
531 |
+
filters=512
|
532 |
+
size=1
|
533 |
+
stride=1
|
534 |
+
pad=1
|
535 |
+
activation=leaky
|
536 |
+
|
537 |
+
[convolutional]
|
538 |
+
batch_normalize=1
|
539 |
+
filters=1024
|
540 |
+
size=3
|
541 |
+
stride=1
|
542 |
+
pad=1
|
543 |
+
activation=leaky
|
544 |
+
|
545 |
+
[shortcut]
|
546 |
+
from=-3
|
547 |
+
activation=linear
|
548 |
+
|
549 |
+
######################
|
550 |
+
|
551 |
+
[convolutional]
|
552 |
+
batch_normalize=1
|
553 |
+
filters=512
|
554 |
+
size=1
|
555 |
+
stride=1
|
556 |
+
pad=1
|
557 |
+
activation=leaky
|
558 |
+
|
559 |
+
[convolutional]
|
560 |
+
batch_normalize=1
|
561 |
+
size=3
|
562 |
+
stride=1
|
563 |
+
pad=1
|
564 |
+
filters=1024
|
565 |
+
activation=leaky
|
566 |
+
|
567 |
+
[convolutional]
|
568 |
+
batch_normalize=1
|
569 |
+
filters=512
|
570 |
+
size=1
|
571 |
+
stride=1
|
572 |
+
pad=1
|
573 |
+
activation=leaky
|
574 |
+
|
575 |
+
[convolutional]
|
576 |
+
batch_normalize=1
|
577 |
+
size=3
|
578 |
+
stride=1
|
579 |
+
pad=1
|
580 |
+
filters=1024
|
581 |
+
activation=leaky
|
582 |
+
|
583 |
+
[convolutional]
|
584 |
+
batch_normalize=1
|
585 |
+
filters=512
|
586 |
+
size=1
|
587 |
+
stride=1
|
588 |
+
pad=1
|
589 |
+
activation=leaky
|
590 |
+
|
591 |
+
[convolutional]
|
592 |
+
batch_normalize=1
|
593 |
+
size=3
|
594 |
+
stride=1
|
595 |
+
pad=1
|
596 |
+
filters=1024
|
597 |
+
activation=leaky
|
598 |
+
|
599 |
+
[convolutional]
|
600 |
+
size=1
|
601 |
+
stride=1
|
602 |
+
pad=1
|
603 |
+
filters=1818
|
604 |
+
activation=linear
|
605 |
+
|
606 |
+
|
607 |
+
[yolo]
|
608 |
+
mask = 6,7,8
|
609 |
+
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
610 |
+
classes=601
|
611 |
+
num=9
|
612 |
+
jitter=.3
|
613 |
+
ignore_thresh = .7
|
614 |
+
truth_thresh = 1
|
615 |
+
random=1
|
616 |
+
|
617 |
+
|
618 |
+
[route]
|
619 |
+
layers = -4
|
620 |
+
|
621 |
+
[convolutional]
|
622 |
+
batch_normalize=1
|
623 |
+
filters=256
|
624 |
+
size=1
|
625 |
+
stride=1
|
626 |
+
pad=1
|
627 |
+
activation=leaky
|
628 |
+
|
629 |
+
[upsample]
|
630 |
+
stride=2
|
631 |
+
|
632 |
+
[route]
|
633 |
+
layers = -1, 61
|
634 |
+
|
635 |
+
|
636 |
+
|
637 |
+
[convolutional]
|
638 |
+
batch_normalize=1
|
639 |
+
filters=256
|
640 |
+
size=1
|
641 |
+
stride=1
|
642 |
+
pad=1
|
643 |
+
activation=leaky
|
644 |
+
|
645 |
+
[convolutional]
|
646 |
+
batch_normalize=1
|
647 |
+
size=3
|
648 |
+
stride=1
|
649 |
+
pad=1
|
650 |
+
filters=512
|
651 |
+
activation=leaky
|
652 |
+
|
653 |
+
[convolutional]
|
654 |
+
batch_normalize=1
|
655 |
+
filters=256
|
656 |
+
size=1
|
657 |
+
stride=1
|
658 |
+
pad=1
|
659 |
+
activation=leaky
|
660 |
+
|
661 |
+
[convolutional]
|
662 |
+
batch_normalize=1
|
663 |
+
size=3
|
664 |
+
stride=1
|
665 |
+
pad=1
|
666 |
+
filters=512
|
667 |
+
activation=leaky
|
668 |
+
|
669 |
+
[convolutional]
|
670 |
+
batch_normalize=1
|
671 |
+
filters=256
|
672 |
+
size=1
|
673 |
+
stride=1
|
674 |
+
pad=1
|
675 |
+
activation=leaky
|
676 |
+
|
677 |
+
[convolutional]
|
678 |
+
batch_normalize=1
|
679 |
+
size=3
|
680 |
+
stride=1
|
681 |
+
pad=1
|
682 |
+
filters=512
|
683 |
+
activation=leaky
|
684 |
+
|
685 |
+
[convolutional]
|
686 |
+
size=1
|
687 |
+
stride=1
|
688 |
+
pad=1
|
689 |
+
filters=1818
|
690 |
+
activation=linear
|
691 |
+
|
692 |
+
|
693 |
+
[yolo]
|
694 |
+
mask = 3,4,5
|
695 |
+
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
696 |
+
classes=601
|
697 |
+
num=9
|
698 |
+
jitter=.3
|
699 |
+
ignore_thresh = .7
|
700 |
+
truth_thresh = 1
|
701 |
+
random=1
|
702 |
+
|
703 |
+
|
704 |
+
|
705 |
+
[route]
|
706 |
+
layers = -4
|
707 |
+
|
708 |
+
[convolutional]
|
709 |
+
batch_normalize=1
|
710 |
+
filters=128
|
711 |
+
size=1
|
712 |
+
stride=1
|
713 |
+
pad=1
|
714 |
+
activation=leaky
|
715 |
+
|
716 |
+
[upsample]
|
717 |
+
stride=2
|
718 |
+
|
719 |
+
[route]
|
720 |
+
layers = -1, 36
|
721 |
+
|
722 |
+
|
723 |
+
|
724 |
+
[convolutional]
|
725 |
+
batch_normalize=1
|
726 |
+
filters=128
|
727 |
+
size=1
|
728 |
+
stride=1
|
729 |
+
pad=1
|
730 |
+
activation=leaky
|
731 |
+
|
732 |
+
[convolutional]
|
733 |
+
batch_normalize=1
|
734 |
+
size=3
|
735 |
+
stride=1
|
736 |
+
pad=1
|
737 |
+
filters=256
|
738 |
+
activation=leaky
|
739 |
+
|
740 |
+
[convolutional]
|
741 |
+
batch_normalize=1
|
742 |
+
filters=128
|
743 |
+
size=1
|
744 |
+
stride=1
|
745 |
+
pad=1
|
746 |
+
activation=leaky
|
747 |
+
|
748 |
+
[convolutional]
|
749 |
+
batch_normalize=1
|
750 |
+
size=3
|
751 |
+
stride=1
|
752 |
+
pad=1
|
753 |
+
filters=256
|
754 |
+
activation=leaky
|
755 |
+
|
756 |
+
[convolutional]
|
757 |
+
batch_normalize=1
|
758 |
+
filters=128
|
759 |
+
size=1
|
760 |
+
stride=1
|
761 |
+
pad=1
|
762 |
+
activation=leaky
|
763 |
+
|
764 |
+
[convolutional]
|
765 |
+
batch_normalize=1
|
766 |
+
size=3
|
767 |
+
stride=1
|
768 |
+
pad=1
|
769 |
+
filters=256
|
770 |
+
activation=leaky
|
771 |
+
|
772 |
+
[convolutional]
|
773 |
+
size=1
|
774 |
+
stride=1
|
775 |
+
pad=1
|
776 |
+
filters=1818
|
777 |
+
activation=linear
|
778 |
+
|
779 |
+
|
780 |
+
[yolo]
|
781 |
+
mask = 0,1,2
|
782 |
+
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
783 |
+
classes=601
|
784 |
+
num=9
|
785 |
+
jitter=.3
|
786 |
+
ignore_thresh = .7
|
787 |
+
truth_thresh = 1
|
788 |
+
random=1
|
789 |
+
|
model/cfg/yolov3-spp.cfg
ADDED
@@ -0,0 +1,822 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[net]
|
2 |
+
# Testing
|
3 |
+
batch=1
|
4 |
+
subdivisions=1
|
5 |
+
# Training
|
6 |
+
# batch=64
|
7 |
+
# subdivisions=16
|
8 |
+
width=608
|
9 |
+
height=608
|
10 |
+
channels=3
|
11 |
+
momentum=0.9
|
12 |
+
decay=0.0005
|
13 |
+
angle=0
|
14 |
+
saturation = 1.5
|
15 |
+
exposure = 1.5
|
16 |
+
hue=.1
|
17 |
+
|
18 |
+
learning_rate=0.001
|
19 |
+
burn_in=1000
|
20 |
+
max_batches = 500200
|
21 |
+
policy=steps
|
22 |
+
steps=400000,450000
|
23 |
+
scales=.1,.1
|
24 |
+
|
25 |
+
[convolutional]
|
26 |
+
batch_normalize=1
|
27 |
+
filters=32
|
28 |
+
size=3
|
29 |
+
stride=1
|
30 |
+
pad=1
|
31 |
+
activation=leaky
|
32 |
+
|
33 |
+
# Downsample
|
34 |
+
|
35 |
+
[convolutional]
|
36 |
+
batch_normalize=1
|
37 |
+
filters=64
|
38 |
+
size=3
|
39 |
+
stride=2
|
40 |
+
pad=1
|
41 |
+
activation=leaky
|
42 |
+
|
43 |
+
[convolutional]
|
44 |
+
batch_normalize=1
|
45 |
+
filters=32
|
46 |
+
size=1
|
47 |
+
stride=1
|
48 |
+
pad=1
|
49 |
+
activation=leaky
|
50 |
+
|
51 |
+
[convolutional]
|
52 |
+
batch_normalize=1
|
53 |
+
filters=64
|
54 |
+
size=3
|
55 |
+
stride=1
|
56 |
+
pad=1
|
57 |
+
activation=leaky
|
58 |
+
|
59 |
+
[shortcut]
|
60 |
+
from=-3
|
61 |
+
activation=linear
|
62 |
+
|
63 |
+
# Downsample
|
64 |
+
|
65 |
+
[convolutional]
|
66 |
+
batch_normalize=1
|
67 |
+
filters=128
|
68 |
+
size=3
|
69 |
+
stride=2
|
70 |
+
pad=1
|
71 |
+
activation=leaky
|
72 |
+
|
73 |
+
[convolutional]
|
74 |
+
batch_normalize=1
|
75 |
+
filters=64
|
76 |
+
size=1
|
77 |
+
stride=1
|
78 |
+
pad=1
|
79 |
+
activation=leaky
|
80 |
+
|
81 |
+
[convolutional]
|
82 |
+
batch_normalize=1
|
83 |
+
filters=128
|
84 |
+
size=3
|
85 |
+
stride=1
|
86 |
+
pad=1
|
87 |
+
activation=leaky
|
88 |
+
|
89 |
+
[shortcut]
|
90 |
+
from=-3
|
91 |
+
activation=linear
|
92 |
+
|
93 |
+
[convolutional]
|
94 |
+
batch_normalize=1
|
95 |
+
filters=64
|
96 |
+
size=1
|
97 |
+
stride=1
|
98 |
+
pad=1
|
99 |
+
activation=leaky
|
100 |
+
|
101 |
+
[convolutional]
|
102 |
+
batch_normalize=1
|
103 |
+
filters=128
|
104 |
+
size=3
|
105 |
+
stride=1
|
106 |
+
pad=1
|
107 |
+
activation=leaky
|
108 |
+
|
109 |
+
[shortcut]
|
110 |
+
from=-3
|
111 |
+
activation=linear
|
112 |
+
|
113 |
+
# Downsample
|
114 |
+
|
115 |
+
[convolutional]
|
116 |
+
batch_normalize=1
|
117 |
+
filters=256
|
118 |
+
size=3
|
119 |
+
stride=2
|
120 |
+
pad=1
|
121 |
+
activation=leaky
|
122 |
+
|
123 |
+
[convolutional]
|
124 |
+
batch_normalize=1
|
125 |
+
filters=128
|
126 |
+
size=1
|
127 |
+
stride=1
|
128 |
+
pad=1
|
129 |
+
activation=leaky
|
130 |
+
|
131 |
+
[convolutional]
|
132 |
+
batch_normalize=1
|
133 |
+
filters=256
|
134 |
+
size=3
|
135 |
+
stride=1
|
136 |
+
pad=1
|
137 |
+
activation=leaky
|
138 |
+
|
139 |
+
[shortcut]
|
140 |
+
from=-3
|
141 |
+
activation=linear
|
142 |
+
|
143 |
+
[convolutional]
|
144 |
+
batch_normalize=1
|
145 |
+
filters=128
|
146 |
+
size=1
|
147 |
+
stride=1
|
148 |
+
pad=1
|
149 |
+
activation=leaky
|
150 |
+
|
151 |
+
[convolutional]
|
152 |
+
batch_normalize=1
|
153 |
+
filters=256
|
154 |
+
size=3
|
155 |
+
stride=1
|
156 |
+
pad=1
|
157 |
+
activation=leaky
|
158 |
+
|
159 |
+
[shortcut]
|
160 |
+
from=-3
|
161 |
+
activation=linear
|
162 |
+
|
163 |
+
[convolutional]
|
164 |
+
batch_normalize=1
|
165 |
+
filters=128
|
166 |
+
size=1
|
167 |
+
stride=1
|
168 |
+
pad=1
|
169 |
+
activation=leaky
|
170 |
+
|
171 |
+
[convolutional]
|
172 |
+
batch_normalize=1
|
173 |
+
filters=256
|
174 |
+
size=3
|
175 |
+
stride=1
|
176 |
+
pad=1
|
177 |
+
activation=leaky
|
178 |
+
|
179 |
+
[shortcut]
|
180 |
+
from=-3
|
181 |
+
activation=linear
|
182 |
+
|
183 |
+
[convolutional]
|
184 |
+
batch_normalize=1
|
185 |
+
filters=128
|
186 |
+
size=1
|
187 |
+
stride=1
|
188 |
+
pad=1
|
189 |
+
activation=leaky
|
190 |
+
|
191 |
+
[convolutional]
|
192 |
+
batch_normalize=1
|
193 |
+
filters=256
|
194 |
+
size=3
|
195 |
+
stride=1
|
196 |
+
pad=1
|
197 |
+
activation=leaky
|
198 |
+
|
199 |
+
[shortcut]
|
200 |
+
from=-3
|
201 |
+
activation=linear
|
202 |
+
|
203 |
+
|
204 |
+
[convolutional]
|
205 |
+
batch_normalize=1
|
206 |
+
filters=128
|
207 |
+
size=1
|
208 |
+
stride=1
|
209 |
+
pad=1
|
210 |
+
activation=leaky
|
211 |
+
|
212 |
+
[convolutional]
|
213 |
+
batch_normalize=1
|
214 |
+
filters=256
|
215 |
+
size=3
|
216 |
+
stride=1
|
217 |
+
pad=1
|
218 |
+
activation=leaky
|
219 |
+
|
220 |
+
[shortcut]
|
221 |
+
from=-3
|
222 |
+
activation=linear
|
223 |
+
|
224 |
+
[convolutional]
|
225 |
+
batch_normalize=1
|
226 |
+
filters=128
|
227 |
+
size=1
|
228 |
+
stride=1
|
229 |
+
pad=1
|
230 |
+
activation=leaky
|
231 |
+
|
232 |
+
[convolutional]
|
233 |
+
batch_normalize=1
|
234 |
+
filters=256
|
235 |
+
size=3
|
236 |
+
stride=1
|
237 |
+
pad=1
|
238 |
+
activation=leaky
|
239 |
+
|
240 |
+
[shortcut]
|
241 |
+
from=-3
|
242 |
+
activation=linear
|
243 |
+
|
244 |
+
[convolutional]
|
245 |
+
batch_normalize=1
|
246 |
+
filters=128
|
247 |
+
size=1
|
248 |
+
stride=1
|
249 |
+
pad=1
|
250 |
+
activation=leaky
|
251 |
+
|
252 |
+
[convolutional]
|
253 |
+
batch_normalize=1
|
254 |
+
filters=256
|
255 |
+
size=3
|
256 |
+
stride=1
|
257 |
+
pad=1
|
258 |
+
activation=leaky
|
259 |
+
|
260 |
+
[shortcut]
|
261 |
+
from=-3
|
262 |
+
activation=linear
|
263 |
+
|
264 |
+
[convolutional]
|
265 |
+
batch_normalize=1
|
266 |
+
filters=128
|
267 |
+
size=1
|
268 |
+
stride=1
|
269 |
+
pad=1
|
270 |
+
activation=leaky
|
271 |
+
|
272 |
+
[convolutional]
|
273 |
+
batch_normalize=1
|
274 |
+
filters=256
|
275 |
+
size=3
|
276 |
+
stride=1
|
277 |
+
pad=1
|
278 |
+
activation=leaky
|
279 |
+
|
280 |
+
[shortcut]
|
281 |
+
from=-3
|
282 |
+
activation=linear
|
283 |
+
|
284 |
+
# Downsample
|
285 |
+
|
286 |
+
[convolutional]
|
287 |
+
batch_normalize=1
|
288 |
+
filters=512
|
289 |
+
size=3
|
290 |
+
stride=2
|
291 |
+
pad=1
|
292 |
+
activation=leaky
|
293 |
+
|
294 |
+
[convolutional]
|
295 |
+
batch_normalize=1
|
296 |
+
filters=256
|
297 |
+
size=1
|
298 |
+
stride=1
|
299 |
+
pad=1
|
300 |
+
activation=leaky
|
301 |
+
|
302 |
+
[convolutional]
|
303 |
+
batch_normalize=1
|
304 |
+
filters=512
|
305 |
+
size=3
|
306 |
+
stride=1
|
307 |
+
pad=1
|
308 |
+
activation=leaky
|
309 |
+
|
310 |
+
[shortcut]
|
311 |
+
from=-3
|
312 |
+
activation=linear
|
313 |
+
|
314 |
+
|
315 |
+
[convolutional]
|
316 |
+
batch_normalize=1
|
317 |
+
filters=256
|
318 |
+
size=1
|
319 |
+
stride=1
|
320 |
+
pad=1
|
321 |
+
activation=leaky
|
322 |
+
|
323 |
+
[convolutional]
|
324 |
+
batch_normalize=1
|
325 |
+
filters=512
|
326 |
+
size=3
|
327 |
+
stride=1
|
328 |
+
pad=1
|
329 |
+
activation=leaky
|
330 |
+
|
331 |
+
[shortcut]
|
332 |
+
from=-3
|
333 |
+
activation=linear
|
334 |
+
|
335 |
+
|
336 |
+
[convolutional]
|
337 |
+
batch_normalize=1
|
338 |
+
filters=256
|
339 |
+
size=1
|
340 |
+
stride=1
|
341 |
+
pad=1
|
342 |
+
activation=leaky
|
343 |
+
|
344 |
+
[convolutional]
|
345 |
+
batch_normalize=1
|
346 |
+
filters=512
|
347 |
+
size=3
|
348 |
+
stride=1
|
349 |
+
pad=1
|
350 |
+
activation=leaky
|
351 |
+
|
352 |
+
[shortcut]
|
353 |
+
from=-3
|
354 |
+
activation=linear
|
355 |
+
|
356 |
+
|
357 |
+
[convolutional]
|
358 |
+
batch_normalize=1
|
359 |
+
filters=256
|
360 |
+
size=1
|
361 |
+
stride=1
|
362 |
+
pad=1
|
363 |
+
activation=leaky
|
364 |
+
|
365 |
+
[convolutional]
|
366 |
+
batch_normalize=1
|
367 |
+
filters=512
|
368 |
+
size=3
|
369 |
+
stride=1
|
370 |
+
pad=1
|
371 |
+
activation=leaky
|
372 |
+
|
373 |
+
[shortcut]
|
374 |
+
from=-3
|
375 |
+
activation=linear
|
376 |
+
|
377 |
+
[convolutional]
|
378 |
+
batch_normalize=1
|
379 |
+
filters=256
|
380 |
+
size=1
|
381 |
+
stride=1
|
382 |
+
pad=1
|
383 |
+
activation=leaky
|
384 |
+
|
385 |
+
[convolutional]
|
386 |
+
batch_normalize=1
|
387 |
+
filters=512
|
388 |
+
size=3
|
389 |
+
stride=1
|
390 |
+
pad=1
|
391 |
+
activation=leaky
|
392 |
+
|
393 |
+
[shortcut]
|
394 |
+
from=-3
|
395 |
+
activation=linear
|
396 |
+
|
397 |
+
|
398 |
+
[convolutional]
|
399 |
+
batch_normalize=1
|
400 |
+
filters=256
|
401 |
+
size=1
|
402 |
+
stride=1
|
403 |
+
pad=1
|
404 |
+
activation=leaky
|
405 |
+
|
406 |
+
[convolutional]
|
407 |
+
batch_normalize=1
|
408 |
+
filters=512
|
409 |
+
size=3
|
410 |
+
stride=1
|
411 |
+
pad=1
|
412 |
+
activation=leaky
|
413 |
+
|
414 |
+
[shortcut]
|
415 |
+
from=-3
|
416 |
+
activation=linear
|
417 |
+
|
418 |
+
|
419 |
+
[convolutional]
|
420 |
+
batch_normalize=1
|
421 |
+
filters=256
|
422 |
+
size=1
|
423 |
+
stride=1
|
424 |
+
pad=1
|
425 |
+
activation=leaky
|
426 |
+
|
427 |
+
[convolutional]
|
428 |
+
batch_normalize=1
|
429 |
+
filters=512
|
430 |
+
size=3
|
431 |
+
stride=1
|
432 |
+
pad=1
|
433 |
+
activation=leaky
|
434 |
+
|
435 |
+
[shortcut]
|
436 |
+
from=-3
|
437 |
+
activation=linear
|
438 |
+
|
439 |
+
[convolutional]
|
440 |
+
batch_normalize=1
|
441 |
+
filters=256
|
442 |
+
size=1
|
443 |
+
stride=1
|
444 |
+
pad=1
|
445 |
+
activation=leaky
|
446 |
+
|
447 |
+
[convolutional]
|
448 |
+
batch_normalize=1
|
449 |
+
filters=512
|
450 |
+
size=3
|
451 |
+
stride=1
|
452 |
+
pad=1
|
453 |
+
activation=leaky
|
454 |
+
|
455 |
+
[shortcut]
|
456 |
+
from=-3
|
457 |
+
activation=linear
|
458 |
+
|
459 |
+
# Downsample
|
460 |
+
|
461 |
+
[convolutional]
|
462 |
+
batch_normalize=1
|
463 |
+
filters=1024
|
464 |
+
size=3
|
465 |
+
stride=2
|
466 |
+
pad=1
|
467 |
+
activation=leaky
|
468 |
+
|
469 |
+
[convolutional]
|
470 |
+
batch_normalize=1
|
471 |
+
filters=512
|
472 |
+
size=1
|
473 |
+
stride=1
|
474 |
+
pad=1
|
475 |
+
activation=leaky
|
476 |
+
|
477 |
+
[convolutional]
|
478 |
+
batch_normalize=1
|
479 |
+
filters=1024
|
480 |
+
size=3
|
481 |
+
stride=1
|
482 |
+
pad=1
|
483 |
+
activation=leaky
|
484 |
+
|
485 |
+
[shortcut]
|
486 |
+
from=-3
|
487 |
+
activation=linear
|
488 |
+
|
489 |
+
[convolutional]
|
490 |
+
batch_normalize=1
|
491 |
+
filters=512
|
492 |
+
size=1
|
493 |
+
stride=1
|
494 |
+
pad=1
|
495 |
+
activation=leaky
|
496 |
+
|
497 |
+
[convolutional]
|
498 |
+
batch_normalize=1
|
499 |
+
filters=1024
|
500 |
+
size=3
|
501 |
+
stride=1
|
502 |
+
pad=1
|
503 |
+
activation=leaky
|
504 |
+
|
505 |
+
[shortcut]
|
506 |
+
from=-3
|
507 |
+
activation=linear
|
508 |
+
|
509 |
+
[convolutional]
|
510 |
+
batch_normalize=1
|
511 |
+
filters=512
|
512 |
+
size=1
|
513 |
+
stride=1
|
514 |
+
pad=1
|
515 |
+
activation=leaky
|
516 |
+
|
517 |
+
[convolutional]
|
518 |
+
batch_normalize=1
|
519 |
+
filters=1024
|
520 |
+
size=3
|
521 |
+
stride=1
|
522 |
+
pad=1
|
523 |
+
activation=leaky
|
524 |
+
|
525 |
+
[shortcut]
|
526 |
+
from=-3
|
527 |
+
activation=linear
|
528 |
+
|
529 |
+
[convolutional]
|
530 |
+
batch_normalize=1
|
531 |
+
filters=512
|
532 |
+
size=1
|
533 |
+
stride=1
|
534 |
+
pad=1
|
535 |
+
activation=leaky
|
536 |
+
|
537 |
+
[convolutional]
|
538 |
+
batch_normalize=1
|
539 |
+
filters=1024
|
540 |
+
size=3
|
541 |
+
stride=1
|
542 |
+
pad=1
|
543 |
+
activation=leaky
|
544 |
+
|
545 |
+
[shortcut]
|
546 |
+
from=-3
|
547 |
+
activation=linear
|
548 |
+
|
549 |
+
######################
|
550 |
+
|
551 |
+
[convolutional]
|
552 |
+
batch_normalize=1
|
553 |
+
filters=512
|
554 |
+
size=1
|
555 |
+
stride=1
|
556 |
+
pad=1
|
557 |
+
activation=leaky
|
558 |
+
|
559 |
+
[convolutional]
|
560 |
+
batch_normalize=1
|
561 |
+
size=3
|
562 |
+
stride=1
|
563 |
+
pad=1
|
564 |
+
filters=1024
|
565 |
+
activation=leaky
|
566 |
+
|
567 |
+
[convolutional]
|
568 |
+
batch_normalize=1
|
569 |
+
filters=512
|
570 |
+
size=1
|
571 |
+
stride=1
|
572 |
+
pad=1
|
573 |
+
activation=leaky
|
574 |
+
|
575 |
+
### SPP ###
|
576 |
+
[maxpool]
|
577 |
+
stride=1
|
578 |
+
size=5
|
579 |
+
|
580 |
+
[route]
|
581 |
+
layers=-2
|
582 |
+
|
583 |
+
[maxpool]
|
584 |
+
stride=1
|
585 |
+
size=9
|
586 |
+
|
587 |
+
[route]
|
588 |
+
layers=-4
|
589 |
+
|
590 |
+
[maxpool]
|
591 |
+
stride=1
|
592 |
+
size=13
|
593 |
+
|
594 |
+
[route]
|
595 |
+
layers=-1,-3,-5,-6
|
596 |
+
|
597 |
+
### End SPP ###
|
598 |
+
|
599 |
+
[convolutional]
|
600 |
+
batch_normalize=1
|
601 |
+
filters=512
|
602 |
+
size=1
|
603 |
+
stride=1
|
604 |
+
pad=1
|
605 |
+
activation=leaky
|
606 |
+
|
607 |
+
|
608 |
+
[convolutional]
|
609 |
+
batch_normalize=1
|
610 |
+
size=3
|
611 |
+
stride=1
|
612 |
+
pad=1
|
613 |
+
filters=1024
|
614 |
+
activation=leaky
|
615 |
+
|
616 |
+
[convolutional]
|
617 |
+
batch_normalize=1
|
618 |
+
filters=512
|
619 |
+
size=1
|
620 |
+
stride=1
|
621 |
+
pad=1
|
622 |
+
activation=leaky
|
623 |
+
|
624 |
+
[convolutional]
|
625 |
+
batch_normalize=1
|
626 |
+
size=3
|
627 |
+
stride=1
|
628 |
+
pad=1
|
629 |
+
filters=1024
|
630 |
+
activation=leaky
|
631 |
+
|
632 |
+
[convolutional]
|
633 |
+
size=1
|
634 |
+
stride=1
|
635 |
+
pad=1
|
636 |
+
filters=255
|
637 |
+
activation=linear
|
638 |
+
|
639 |
+
|
640 |
+
[yolo]
|
641 |
+
mask = 6,7,8
|
642 |
+
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
643 |
+
classes=80
|
644 |
+
num=9
|
645 |
+
jitter=.3
|
646 |
+
ignore_thresh = .7
|
647 |
+
truth_thresh = 1
|
648 |
+
random=1
|
649 |
+
|
650 |
+
|
651 |
+
[route]
|
652 |
+
layers = -4
|
653 |
+
|
654 |
+
[convolutional]
|
655 |
+
batch_normalize=1
|
656 |
+
filters=256
|
657 |
+
size=1
|
658 |
+
stride=1
|
659 |
+
pad=1
|
660 |
+
activation=leaky
|
661 |
+
|
662 |
+
[upsample]
|
663 |
+
stride=2
|
664 |
+
|
665 |
+
[route]
|
666 |
+
layers = -1, 61
|
667 |
+
|
668 |
+
|
669 |
+
|
670 |
+
[convolutional]
|
671 |
+
batch_normalize=1
|
672 |
+
filters=256
|
673 |
+
size=1
|
674 |
+
stride=1
|
675 |
+
pad=1
|
676 |
+
activation=leaky
|
677 |
+
|
678 |
+
[convolutional]
|
679 |
+
batch_normalize=1
|
680 |
+
size=3
|
681 |
+
stride=1
|
682 |
+
pad=1
|
683 |
+
filters=512
|
684 |
+
activation=leaky
|
685 |
+
|
686 |
+
[convolutional]
|
687 |
+
batch_normalize=1
|
688 |
+
filters=256
|
689 |
+
size=1
|
690 |
+
stride=1
|
691 |
+
pad=1
|
692 |
+
activation=leaky
|
693 |
+
|
694 |
+
[convolutional]
|
695 |
+
batch_normalize=1
|
696 |
+
size=3
|
697 |
+
stride=1
|
698 |
+
pad=1
|
699 |
+
filters=512
|
700 |
+
activation=leaky
|
701 |
+
|
702 |
+
[convolutional]
|
703 |
+
batch_normalize=1
|
704 |
+
filters=256
|
705 |
+
size=1
|
706 |
+
stride=1
|
707 |
+
pad=1
|
708 |
+
activation=leaky
|
709 |
+
|
710 |
+
[convolutional]
|
711 |
+
batch_normalize=1
|
712 |
+
size=3
|
713 |
+
stride=1
|
714 |
+
pad=1
|
715 |
+
filters=512
|
716 |
+
activation=leaky
|
717 |
+
|
718 |
+
[convolutional]
|
719 |
+
size=1
|
720 |
+
stride=1
|
721 |
+
pad=1
|
722 |
+
filters=255
|
723 |
+
activation=linear
|
724 |
+
|
725 |
+
|
726 |
+
[yolo]
|
727 |
+
mask = 3,4,5
|
728 |
+
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
729 |
+
classes=80
|
730 |
+
num=9
|
731 |
+
jitter=.3
|
732 |
+
ignore_thresh = .7
|
733 |
+
truth_thresh = 1
|
734 |
+
random=1
|
735 |
+
|
736 |
+
|
737 |
+
|
738 |
+
[route]
|
739 |
+
layers = -4
|
740 |
+
|
741 |
+
[convolutional]
|
742 |
+
batch_normalize=1
|
743 |
+
filters=128
|
744 |
+
size=1
|
745 |
+
stride=1
|
746 |
+
pad=1
|
747 |
+
activation=leaky
|
748 |
+
|
749 |
+
[upsample]
|
750 |
+
stride=2
|
751 |
+
|
752 |
+
[route]
|
753 |
+
layers = -1, 36
|
754 |
+
|
755 |
+
|
756 |
+
|
757 |
+
[convolutional]
|
758 |
+
batch_normalize=1
|
759 |
+
filters=128
|
760 |
+
size=1
|
761 |
+
stride=1
|
762 |
+
pad=1
|
763 |
+
activation=leaky
|
764 |
+
|
765 |
+
[convolutional]
|
766 |
+
batch_normalize=1
|
767 |
+
size=3
|
768 |
+
stride=1
|
769 |
+
pad=1
|
770 |
+
filters=256
|
771 |
+
activation=leaky
|
772 |
+
|
773 |
+
[convolutional]
|
774 |
+
batch_normalize=1
|
775 |
+
filters=128
|
776 |
+
size=1
|
777 |
+
stride=1
|
778 |
+
pad=1
|
779 |
+
activation=leaky
|
780 |
+
|
781 |
+
[convolutional]
|
782 |
+
batch_normalize=1
|
783 |
+
size=3
|
784 |
+
stride=1
|
785 |
+
pad=1
|
786 |
+
filters=256
|
787 |
+
activation=leaky
|
788 |
+
|
789 |
+
[convolutional]
|
790 |
+
batch_normalize=1
|
791 |
+
filters=128
|
792 |
+
size=1
|
793 |
+
stride=1
|
794 |
+
pad=1
|
795 |
+
activation=leaky
|
796 |
+
|
797 |
+
[convolutional]
|
798 |
+
batch_normalize=1
|
799 |
+
size=3
|
800 |
+
stride=1
|
801 |
+
pad=1
|
802 |
+
filters=256
|
803 |
+
activation=leaky
|
804 |
+
|
805 |
+
[convolutional]
|
806 |
+
size=1
|
807 |
+
stride=1
|
808 |
+
pad=1
|
809 |
+
filters=255
|
810 |
+
activation=linear
|
811 |
+
|
812 |
+
|
813 |
+
[yolo]
|
814 |
+
mask = 0,1,2
|
815 |
+
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
|
816 |
+
classes=80
|
817 |
+
num=9
|
818 |
+
jitter=.3
|
819 |
+
ignore_thresh = .7
|
820 |
+
truth_thresh = 1
|
821 |
+
random=1
|
822 |
+
|