flatala-research commited on
Commit
79e13d3
1 Parent(s): 37791d6

Training in progress, epoch 0

Browse files
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MCG-NJU/videomae-base-finetuned-kinetics",
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": "DOWN",
16
+ "1": "FOREWARD",
17
+ "2": "LEFT",
18
+ "3": "NO_MOVEMENT",
19
+ "4": "RIGHT",
20
+ "5": "ROTATION",
21
+ "6": "SELF",
22
+ "7": "UP"
23
+ },
24
+ "image_size": 224,
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "DOWN": 0,
29
+ "FOREWARD": 1,
30
+ "LEFT": 2,
31
+ "NO_MOVEMENT": 3,
32
+ "RIGHT": 4,
33
+ "ROTATION": 5,
34
+ "SELF": 6,
35
+ "UP": 7
36
+ },
37
+ "layer_norm_eps": 1e-12,
38
+ "model_type": "videomae",
39
+ "norm_pix_loss": false,
40
+ "num_attention_heads": 12,
41
+ "num_channels": 3,
42
+ "num_frames": 16,
43
+ "num_hidden_layers": 12,
44
+ "patch_size": 16,
45
+ "problem_type": "single_label_classification",
46
+ "qkv_bias": true,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.41.0",
49
+ "tubelet_size": 2,
50
+ "use_mean_pooling": true
51
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d791630e1553125f8f7f952853f4f5b94f84596f4055f0f6385eab9e8dc13b07
3
+ size 344955792
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:b8f0dfbd8e205c10620fa7beaefbf7a9395d7ea1321adac10a5cce3403cde6d7
3
+ size 4719