Commit
•
dd7d20c
1
Parent(s):
503f502
Training in progress, epoch 0
Browse files- .gitignore +1 -0
- config.json +65 -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 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "tap dancing",
|
16 |
+
"1": "breakdancing",
|
17 |
+
"2": "belly dancing",
|
18 |
+
"3": "dancing charleston",
|
19 |
+
"4": "dancing ballet",
|
20 |
+
"5": "square dancing",
|
21 |
+
"6": "jumpstyle dancing",
|
22 |
+
"7": "salsa dancing",
|
23 |
+
"8": "robot dancing",
|
24 |
+
"9": "country line dancing",
|
25 |
+
"10": "dancing macarena",
|
26 |
+
"11": "mosh pit dancing",
|
27 |
+
"12": "dancing gangnam style",
|
28 |
+
"13": "swing dancing",
|
29 |
+
"14": "tango dancing"
|
30 |
+
},
|
31 |
+
"image_size": 224,
|
32 |
+
"initializer_range": 0.02,
|
33 |
+
"intermediate_size": 3072,
|
34 |
+
"label2id": {
|
35 |
+
"belly dancing": 2,
|
36 |
+
"breakdancing": 1,
|
37 |
+
"country line dancing": 9,
|
38 |
+
"dancing ballet": 4,
|
39 |
+
"dancing charleston": 3,
|
40 |
+
"dancing gangnam style": 12,
|
41 |
+
"dancing macarena": 10,
|
42 |
+
"jumpstyle dancing": 6,
|
43 |
+
"mosh pit dancing": 11,
|
44 |
+
"robot dancing": 8,
|
45 |
+
"salsa dancing": 7,
|
46 |
+
"square dancing": 5,
|
47 |
+
"swing dancing": 13,
|
48 |
+
"tango dancing": 14,
|
49 |
+
"tap dancing": 0
|
50 |
+
},
|
51 |
+
"layer_norm_eps": 1e-12,
|
52 |
+
"model_type": "videomae",
|
53 |
+
"norm_pix_loss": true,
|
54 |
+
"num_attention_heads": 12,
|
55 |
+
"num_channels": 3,
|
56 |
+
"num_frames": 16,
|
57 |
+
"num_hidden_layers": 12,
|
58 |
+
"patch_size": 16,
|
59 |
+
"problem_type": "single_label_classification",
|
60 |
+
"qkv_bias": true,
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.30.1",
|
63 |
+
"tubelet_size": 2,
|
64 |
+
"use_mean_pooling": false
|
65 |
+
}
|
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:e95f301ebedd72dd60c4e5e6b1a056e17a1e905464265e8086132277a5607bf0
|
3 |
+
size 345018933
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e859548f37d8fcf1dadafacc79a9e05b2c2b307146539e6a8a2236d720c1c92
|
3 |
+
size 3963
|