Hugging Face's logo

RodrigoFardin
/
videomae-base-finetuned-dd

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
RodrigoFardin commited on
Commit
c0b84a7
•
1 Parent(s): 767d475

Training in progress, epoch 2

Browse files
Files changed (5) hide show
  1. config.json +39 -39
  2. model.safetensors +1 -1
  3. preprocessor_config.json +42 -42
  4. runs/May17_12-37-24_f196d5c16057/events.out.tfevents.1715951494.f196d5c16057.34.0 +2 -2
  5. training_args.bin +2 -2
config.json CHANGED
@@ -1,39 +1,39 @@
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": "falso_alarme",
16
- "1": "sonolencia"
17
- },
18
- "image_size": 224,
19
- "initializer_range": 0.02,
20
- "intermediate_size": 3072,
21
- "label2id": {
22
- "falso_alarme": 0,
23
- "sonolencia": 1
24
- },
25
- "layer_norm_eps": 1e-12,
26
- "model_type": "videomae",
27
- "norm_pix_loss": true,
28
- "num_attention_heads": 12,
29
- "num_channels": 3,
30
- "num_frames": 16,
31
- "num_hidden_layers": 12,
32
- "patch_size": 16,
33
- "problem_type": "single_label_classification",
34
- "qkv_bias": true,
35
- "torch_dtype": "float32",
36
- "transformers_version": "4.40.2",
37
- "tubelet_size": 2,
38
- "use_mean_pooling": false
39
- }
 
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": "falso_alarme",
16
+ "1": "sonolencia"
17
+ },
18
+ "image_size": 224,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "falso_alarme": 0,
23
+ "sonolencia": 1
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "model_type": "videomae",
27
+ "norm_pix_loss": true,
28
+ "num_attention_heads": 12,
29
+ "num_channels": 3,
30
+ "num_frames": 16,
31
+ "num_hidden_layers": 12,
32
+ "patch_size": 16,
33
+ "problem_type": "single_label_classification",
34
+ "qkv_bias": true,
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.39.3",
37
+ "tubelet_size": 2,
38
+ "use_mean_pooling": false
39
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dea590794164198d0db6723041bcbd536fef9748d8abfe7f8fa5a5443c45267d
3
  size 344937368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bf1d8ed0f02a4c9ef6f59f79983909e9159c872d40be34b83c3f7ea50123be6
3
  size 344937368
preprocessor_config.json CHANGED
@@ -1,42 +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
- }
 
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
+ }
runs/May17_12-37-24_f196d5c16057/events.out.tfevents.1715951494.f196d5c16057.34.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:89a5d18de419910991e024c55396a8806f029d65127ce44dab93a7e7510f2f62
3
- size 12457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:971c28a88d42385332d8f5d08dec8d303bea536909e972b63eb5fe419439f280
3
+ size 16367
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c37194c7efe8996375d9968dfbd73b3102c47371d6ba06f03e23a1e7a02a018
3
- size 4527
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63ff2b70d0e3bf15c766db0d38b81729bf0e25d8d4dc0a979a025a16674b1017
3
+ size 4984