Training in progress, epoch 0
Browse files- .gitignore +1 -0
- config.json +59 -0
- preprocessor_config.json +27 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "MCG-NJU/videomae-base",
|
3 |
+
"architectures": [
|
4 |
+
"VideoMAEForVideoClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"decoder_hidden_size": 384,
|
8 |
+
"decoder_intermediate_size": 1536,
|
9 |
+
"decoder_num_attention_heads": 6,
|
10 |
+
"decoder_num_hidden_layers": 4,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.0,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "bending_bad",
|
16 |
+
"1": "bending_good",
|
17 |
+
"2": "carry_n_walk_bad",
|
18 |
+
"3": "carry_n_walk_good",
|
19 |
+
"4": "lifting_bad",
|
20 |
+
"5": "lifting_good",
|
21 |
+
"6": "pull_bad",
|
22 |
+
"7": "pull_good",
|
23 |
+
"8": "push_bad",
|
24 |
+
"9": "push_good",
|
25 |
+
"10": "twist_bad",
|
26 |
+
"11": "twist_good"
|
27 |
+
},
|
28 |
+
"image_size": 224,
|
29 |
+
"initializer_range": 0.02,
|
30 |
+
"intermediate_size": 3072,
|
31 |
+
"label2id": {
|
32 |
+
"bending_bad": 0,
|
33 |
+
"bending_good": 1,
|
34 |
+
"carry_n_walk_bad": 2,
|
35 |
+
"carry_n_walk_good": 3,
|
36 |
+
"lifting_bad": 4,
|
37 |
+
"lifting_good": 5,
|
38 |
+
"pull_bad": 6,
|
39 |
+
"pull_good": 7,
|
40 |
+
"push_bad": 8,
|
41 |
+
"push_good": 9,
|
42 |
+
"twist_bad": 10,
|
43 |
+
"twist_good": 11
|
44 |
+
},
|
45 |
+
"layer_norm_eps": 1e-12,
|
46 |
+
"model_type": "videomae",
|
47 |
+
"norm_pix_loss": true,
|
48 |
+
"num_attention_heads": 12,
|
49 |
+
"num_channels": 3,
|
50 |
+
"num_frames": 16,
|
51 |
+
"num_hidden_layers": 12,
|
52 |
+
"patch_size": 16,
|
53 |
+
"problem_type": "single_label_classification",
|
54 |
+
"qkv_bias": true,
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.29.1",
|
57 |
+
"tubelet_size": 2,
|
58 |
+
"use_mean_pooling": false
|
59 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 224,
|
4 |
+
"width": 224
|
5 |
+
},
|
6 |
+
"do_center_crop": true,
|
7 |
+
"do_normalize": true,
|
8 |
+
"do_rescale": true,
|
9 |
+
"do_resize": true,
|
10 |
+
"feature_extractor_type": "VideoMAEFeatureExtractor",
|
11 |
+
"image_mean": [
|
12 |
+
0.485,
|
13 |
+
0.456,
|
14 |
+
0.406
|
15 |
+
],
|
16 |
+
"image_processor_type": "VideoMAEImageProcessor",
|
17 |
+
"image_std": [
|
18 |
+
0.229,
|
19 |
+
0.224,
|
20 |
+
0.225
|
21 |
+
],
|
22 |
+
"resample": 2,
|
23 |
+
"rescale_factor": 0.00392156862745098,
|
24 |
+
"size": {
|
25 |
+
"shortest_edge": 224
|
26 |
+
}
|
27 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37e490ec5def2af804fb331c900a51a76f5ed8431def663a4fa83756a8b95bb5
|
3 |
+
size 345009653
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acf75445e8faeb3d20cddde0414cd681b72785cf2435c7d82caf4f1b9e601fb9
|
3 |
+
size 3963
|