Training in progress, epoch 0
Browse files- config.json +55 -0
- model.safetensors +3 -0
- preprocessor_config.json +42 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "ApplyEyeMakeup",
|
16 |
+
"1": "ApplyLipstick",
|
17 |
+
"2": "Archery",
|
18 |
+
"3": "BabyCrawling",
|
19 |
+
"4": "BalanceBeam",
|
20 |
+
"5": "BandMarching",
|
21 |
+
"6": "BaseballPitch",
|
22 |
+
"7": "Basketball",
|
23 |
+
"8": "BasketballDunk",
|
24 |
+
"9": "BenchPress"
|
25 |
+
},
|
26 |
+
"image_size": 224,
|
27 |
+
"initializer_range": 0.02,
|
28 |
+
"intermediate_size": 3072,
|
29 |
+
"label2id": {
|
30 |
+
"ApplyEyeMakeup": 0,
|
31 |
+
"ApplyLipstick": 1,
|
32 |
+
"Archery": 2,
|
33 |
+
"BabyCrawling": 3,
|
34 |
+
"BalanceBeam": 4,
|
35 |
+
"BandMarching": 5,
|
36 |
+
"BaseballPitch": 6,
|
37 |
+
"Basketball": 7,
|
38 |
+
"BasketballDunk": 8,
|
39 |
+
"BenchPress": 9
|
40 |
+
},
|
41 |
+
"layer_norm_eps": 1e-12,
|
42 |
+
"model_type": "videomae",
|
43 |
+
"norm_pix_loss": true,
|
44 |
+
"num_attention_heads": 12,
|
45 |
+
"num_channels": 3,
|
46 |
+
"num_frames": 16,
|
47 |
+
"num_hidden_layers": 12,
|
48 |
+
"patch_size": 16,
|
49 |
+
"problem_type": "single_label_classification",
|
50 |
+
"qkv_bias": true,
|
51 |
+
"torch_dtype": "float32",
|
52 |
+
"transformers_version": "4.41.2",
|
53 |
+
"tubelet_size": 2,
|
54 |
+
"use_mean_pooling": false
|
55 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d044a1722165ce83d87a552bb8377a24684d571f293bb4e2fff5ae7ca94625a6
|
3 |
+
size 344961984
|
preprocessor_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"videos",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_center_crop",
|
8 |
+
"crop_size",
|
9 |
+
"do_rescale",
|
10 |
+
"rescale_factor",
|
11 |
+
"do_normalize",
|
12 |
+
"image_mean",
|
13 |
+
"image_std",
|
14 |
+
"return_tensors",
|
15 |
+
"data_format",
|
16 |
+
"input_data_format"
|
17 |
+
],
|
18 |
+
"crop_size": {
|
19 |
+
"height": 224,
|
20 |
+
"width": 224
|
21 |
+
},
|
22 |
+
"do_center_crop": true,
|
23 |
+
"do_normalize": true,
|
24 |
+
"do_rescale": true,
|
25 |
+
"do_resize": true,
|
26 |
+
"image_mean": [
|
27 |
+
0.485,
|
28 |
+
0.456,
|
29 |
+
0.406
|
30 |
+
],
|
31 |
+
"image_processor_type": "VideoMAEImageProcessor",
|
32 |
+
"image_std": [
|
33 |
+
0.229,
|
34 |
+
0.224,
|
35 |
+
0.225
|
36 |
+
],
|
37 |
+
"resample": 2,
|
38 |
+
"rescale_factor": 0.00392156862745098,
|
39 |
+
"size": {
|
40 |
+
"shortest_edge": 224
|
41 |
+
}
|
42 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85b7a8088074871e97f7662a1ac6a55042e3605e19cce374c9a942c5fccb2fe4
|
3 |
+
size 4667
|