ahsanshahid2882 commited on
Commit
05d903f
1 Parent(s): a638c9c

Training in progress, epoch 0

Browse files
config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "falling",
16
+ "1": "hitting",
17
+ "2": "kicking",
18
+ "3": "neutral",
19
+ "4": "running",
20
+ "5": "sitting",
21
+ "6": "stealing",
22
+ "7": "vandalizing",
23
+ "8": "walking"
24
+ },
25
+ "image_size": 224,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 3072,
28
+ "label2id": {
29
+ "falling": 0,
30
+ "hitting": 1,
31
+ "kicking": 2,
32
+ "neutral": 3,
33
+ "running": 4,
34
+ "sitting": 5,
35
+ "stealing": 6,
36
+ "vandalizing": 7,
37
+ "walking": 8
38
+ },
39
+ "layer_norm_eps": 1e-12,
40
+ "model_type": "videomae",
41
+ "norm_pix_loss": true,
42
+ "num_attention_heads": 12,
43
+ "num_channels": 3,
44
+ "num_frames": 16,
45
+ "num_hidden_layers": 12,
46
+ "patch_size": 16,
47
+ "problem_type": "single_label_classification",
48
+ "qkv_bias": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.41.2",
51
+ "tubelet_size": 2,
52
+ "use_mean_pooling": false
53
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9a428aef31b5b61555c8c095a4c8ddae3ed0f25442d3cc804650eff5f591ba
3
+ size 344958908
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:d4179ac4e219801b75700bef5cfdbdca7f17553d921c4760ed8a166514e81cb9
3
+ size 5112