Hugging Face's logo

bmedeiros
/
swin-tiny-patch4-window7-224-finetuned-eurosat

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
bmedeiros commited on
Commit
194aa8e
·
verified ·
1 Parent(s): 9af3f63

Model save

Browse files
Files changed (3) hide show
  1. README.md +61 -46
  2. model.safetensors +1 -1
  3. runs/Dec09_18-28-48_c9ba084c85bf/events.out.tfevents.1733768937.c9ba084c85bf.5668.2 +2 -2
README.md CHANGED
@@ -18,12 +18,12 @@ model-index:
18
  name: imagefolder
19
  type: imagefolder
20
  config: default
21
- split: train
22
  args: default
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
- value: 0.7674418604651163
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 0.4778
37
- - Accuracy: 0.7674
38
 
39
  ## Model description
40
 
@@ -62,51 +62,66 @@ The following hyperparameters were used during training:
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
- - num_epochs: 40
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
71
- | No log | 0.96 | 6 | 0.5581 | 0.6860 |
72
- | 0.5082 | 1.92 | 12 | 0.5865 | 0.6628 |
73
- | 0.5082 | 2.88 | 18 | 0.5983 | 0.6860 |
74
- | 0.4618 | 4.0 | 25 | 0.6791 | 0.6744 |
75
- | 0.3901 | 4.96 | 31 | 0.5642 | 0.7326 |
76
- | 0.3901 | 5.92 | 37 | 0.5044 | 0.7093 |
77
- | 0.4175 | 6.88 | 43 | 0.5285 | 0.6977 |
78
- | 0.4308 | 8.0 | 50 | 0.5152 | 0.7093 |
79
- | 0.4308 | 8.96 | 56 | 0.5628 | 0.7209 |
80
- | 0.3998 | 9.92 | 62 | 0.5401 | 0.7674 |
81
- | 0.3998 | 10.88 | 68 | 0.5199 | 0.7791 |
82
- | 0.3682 | 12.0 | 75 | 0.5043 | 0.7907 |
83
- | 0.3528 | 12.96 | 81 | 0.4796 | 0.7791 |
84
- | 0.3528 | 13.92 | 87 | 0.4938 | 0.7791 |
85
- | 0.3324 | 14.88 | 93 | 0.4879 | 0.7558 |
86
- | 0.3579 | 16.0 | 100 | 0.4972 | 0.8023 |
87
- | 0.3579 | 16.96 | 106 | 0.4579 | 0.7674 |
88
- | 0.3566 | 17.92 | 112 | 0.4891 | 0.7791 |
89
- | 0.3566 | 18.88 | 118 | 0.4654 | 0.8023 |
90
- | 0.3382 | 20.0 | 125 | 0.4672 | 0.7907 |
91
- | 0.3534 | 20.96 | 131 | 0.4688 | 0.7791 |
92
- | 0.3534 | 21.92 | 137 | 0.4891 | 0.7558 |
93
- | 0.3462 | 22.88 | 143 | 0.5025 | 0.7442 |
94
- | 0.3208 | 24.0 | 150 | 0.5026 | 0.7674 |
95
- | 0.3208 | 24.96 | 156 | 0.4936 | 0.7674 |
96
- | 0.3408 | 25.92 | 162 | 0.4607 | 0.7791 |
97
- | 0.3408 | 26.88 | 168 | 0.4420 | 0.7907 |
98
- | 0.333 | 28.0 | 175 | 0.4296 | 0.7907 |
99
- | 0.3169 | 28.96 | 181 | 0.4503 | 0.7907 |
100
- | 0.3169 | 29.92 | 187 | 0.4894 | 0.8023 |
101
- | 0.3267 | 30.88 | 193 | 0.4838 | 0.7907 |
102
- | 0.3114 | 32.0 | 200 | 0.5220 | 0.7791 |
103
- | 0.3114 | 32.96 | 206 | 0.4920 | 0.7791 |
104
- | 0.3143 | 33.92 | 212 | 0.4810 | 0.7442 |
105
- | 0.3143 | 34.88 | 218 | 0.4829 | 0.7558 |
106
- | 0.3034 | 36.0 | 225 | 0.4835 | 0.7674 |
107
- | 0.2944 | 36.96 | 231 | 0.4812 | 0.7791 |
108
- | 0.2944 | 37.92 | 237 | 0.4780 | 0.7674 |
109
- | 0.3018 | 38.4 | 240 | 0.4778 | 0.7674 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
110
 
111
 
112
  ### Framework versions
 
18
  name: imagefolder
19
  type: imagefolder
20
  config: default
21
+ split: test
22
  args: default
23
  metrics:
24
  - name: Accuracy
25
  type: accuracy
26
+ value: 0.7395626242544732
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 0.5320
37
+ - Accuracy: 0.7396
38
 
39
  ## Model description
40
 
 
62
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
  - lr_scheduler_type: linear
64
  - lr_scheduler_warmup_ratio: 0.1
65
+ - num_epochs: 60
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
70
+ |:-------------:|:-------:|:----:|:---------------:|:--------:|
71
+ | No log | 0.8889 | 6 | 0.6376 | 0.6899 |
72
+ | 0.6757 | 1.9259 | 13 | 0.6053 | 0.6938 |
73
+ | 0.5472 | 2.9630 | 20 | 0.5903 | 0.7256 |
74
+ | 0.5472 | 4.0 | 27 | 0.5782 | 0.7316 |
75
+ | 0.4628 | 4.8889 | 33 | 0.5979 | 0.7455 |
76
+ | 0.4181 | 5.9259 | 40 | 0.5735 | 0.7614 |
77
+ | 0.4181 | 6.9630 | 47 | 0.5252 | 0.7495 |
78
+ | 0.4079 | 8.0 | 54 | 0.5363 | 0.7475 |
79
+ | 0.4102 | 8.8889 | 60 | 0.5289 | 0.7495 |
80
+ | 0.4102 | 9.9259 | 67 | 0.5227 | 0.7535 |
81
+ | 0.373 | 10.9630 | 74 | 0.4677 | 0.7773 |
82
+ | 0.3639 | 12.0 | 81 | 0.4978 | 0.7813 |
83
+ | 0.3639 | 12.8889 | 87 | 0.4651 | 0.7992 |
84
+ | 0.3779 | 13.9259 | 94 | 0.4738 | 0.7913 |
85
+ | 0.3476 | 14.9630 | 101 | 0.4697 | 0.8072 |
86
+ | 0.3476 | 16.0 | 108 | 0.4719 | 0.7952 |
87
+ | 0.3467 | 16.8889 | 114 | 0.4552 | 0.7893 |
88
+ | 0.3496 | 17.9259 | 121 | 0.5186 | 0.7714 |
89
+ | 0.3496 | 18.9630 | 128 | 0.4575 | 0.7952 |
90
+ | 0.3657 | 20.0 | 135 | 0.4764 | 0.7793 |
91
+ | 0.3888 | 20.8889 | 141 | 0.5009 | 0.7714 |
92
+ | 0.3888 | 21.9259 | 148 | 0.4673 | 0.7813 |
93
+ | 0.3236 | 22.9630 | 155 | 0.4931 | 0.7753 |
94
+ | 0.3179 | 24.0 | 162 | 0.4837 | 0.7654 |
95
+ | 0.3179 | 24.8889 | 168 | 0.4652 | 0.7694 |
96
+ | 0.327 | 25.9259 | 175 | 0.5108 | 0.7495 |
97
+ | 0.3253 | 26.9630 | 182 | 0.4424 | 0.7833 |
98
+ | 0.3253 | 28.0 | 189 | 0.5622 | 0.7336 |
99
+ | 0.3382 | 28.8889 | 195 | 0.5068 | 0.7694 |
100
+ | 0.331 | 29.9259 | 202 | 0.4530 | 0.7694 |
101
+ | 0.331 | 30.9630 | 209 | 0.5205 | 0.7316 |
102
+ | 0.3302 | 32.0 | 216 | 0.4386 | 0.7853 |
103
+ | 0.2972 | 32.8889 | 222 | 0.5031 | 0.7773 |
104
+ | 0.2972 | 33.9259 | 229 | 0.4909 | 0.7575 |
105
+ | 0.3121 | 34.9630 | 236 | 0.4766 | 0.7793 |
106
+ | 0.2956 | 36.0 | 243 | 0.5262 | 0.7416 |
107
+ | 0.2956 | 36.8889 | 249 | 0.5374 | 0.7316 |
108
+ | 0.2947 | 37.9259 | 256 | 0.4888 | 0.7674 |
109
+ | 0.2662 | 38.9630 | 263 | 0.4881 | 0.7694 |
110
+ | 0.2826 | 40.0 | 270 | 0.4669 | 0.7893 |
111
+ | 0.2826 | 40.8889 | 276 | 0.4591 | 0.7972 |
112
+ | 0.2768 | 41.9259 | 283 | 0.5090 | 0.7575 |
113
+ | 0.2836 | 42.9630 | 290 | 0.5250 | 0.7495 |
114
+ | 0.2836 | 44.0 | 297 | 0.4748 | 0.7654 |
115
+ | 0.2724 | 44.8889 | 303 | 0.4429 | 0.7833 |
116
+ | 0.2498 | 45.9259 | 310 | 0.4460 | 0.7893 |
117
+ | 0.2498 | 46.9630 | 317 | 0.4722 | 0.7793 |
118
+ | 0.2893 | 48.0 | 324 | 0.4799 | 0.7714 |
119
+ | 0.2618 | 48.8889 | 330 | 0.4850 | 0.7714 |
120
+ | 0.2618 | 49.9259 | 337 | 0.5152 | 0.7495 |
121
+ | 0.2664 | 50.9630 | 344 | 0.5347 | 0.7396 |
122
+ | 0.27 | 52.0 | 351 | 0.5343 | 0.7416 |
123
+ | 0.27 | 52.8889 | 357 | 0.5330 | 0.7416 |
124
+ | 0.2539 | 53.3333 | 360 | 0.5320 | 0.7396 |
125
 
126
 
127
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c95d9700b08230de2dc59f1b05b68eceed0e687902a1eeb02d32fd26a104e3fe
3
  size 110342832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7811e91a155b364065512e9f96b87a0344b29751af3020a3854be900364c250f
3
  size 110342832
runs/Dec09_18-28-48_c9ba084c85bf/events.out.tfevents.1733768937.c9ba084c85bf.5668.2 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5200d719d3af0d34e2b95ae962d3dd3227489f2e4fc2c16ece1faafe7207444b
3
- size 29719
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39add8cee326cbd91a16b5ee154263dfbe149299f1a36c031aed18b502b974f0
3
+ size 30607