Hugging Face's logo

kkumtori
/
vivit-b-16x2-kinetics400-0511-mediapipe

Video Classification
Transformers
TensorBoard
Safetensors
vivit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
kkumtori commited on
Commit
bdeb554
•
1 Parent(s): d816784

Training in progress, epoch 0

Browse files
Files changed (5) hide show
  1. config.json +56 -0
  2. model.safetensors +3 -0
  3. preprocessor_config.json +44 -0
  4. runs/May11_05-54-19_c8b476f1f9fa/events.out.tfevents.1715406958.c8b476f1f9fa.1848.0 +3 -0
  5. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vivit-b-16x2-kinetics400",
3
+ "architectures": [
4
+ "VivitForVideoClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "hidden_act": "gelu_fast",
8
+ "hidden_dropout_prob": 0.0,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "\u1100\u1161\u1105\u1167\u11b8\u1103\u1161",
12
+ "1": "\u1100\u1169\u11af\u110c\u1165\u11af",
13
+ "2": "\u1100\u116e\u1100\u1173\u11b8\u110e\u1161",
14
+ "3": "\u1103\u1161\u1105\u1175",
15
+ "4": "\u1107\u1162\u1100\u1169\u1111\u1173\u1103\u1161",
16
+ "5": "\u1107\u1167\u11bc\u110b\u116f\u11ab",
17
+ "6": "\u1107\u116e\u11bc\u1103\u1162",
18
+ "7": "\u110a\u1173\u1105\u1165\u110c\u1175\u1103\u1161",
19
+ "8": "\u110b\u1174\u1109\u1161",
20
+ "9": "\u110e\u1175\u11ab\u1100\u116e"
21
+ },
22
+ "image_size": 224,
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "\u1100\u1161\u1105\u1167\u11b8\u1103\u1161": 0,
27
+ "\u1100\u1169\u11af\u110c\u1165\u11af": 1,
28
+ "\u1100\u116e\u1100\u1173\u11b8\u110e\u1161": 2,
29
+ "\u1103\u1161\u1105\u1175": 3,
30
+ "\u1107\u1162\u1100\u1169\u1111\u1173\u1103\u1161": 4,
31
+ "\u1107\u1167\u11bc\u110b\u116f\u11ab": 5,
32
+ "\u1107\u116e\u11bc\u1103\u1162": 6,
33
+ "\u110a\u1173\u1105\u1165\u110c\u1175\u1103\u1161": 7,
34
+ "\u110b\u1174\u1109\u1161": 8,
35
+ "\u110e\u1175\u11ab\u1100\u116e": 9
36
+ },
37
+ "layer_norm_eps": 1e-06,
38
+ "model_type": "vivit",
39
+ "num_attention_heads": 12,
40
+ "num_channels": 3,
41
+ "num_frames": 32,
42
+ "num_hidden_layers": 12,
43
+ "qkv_bias": true,
44
+ "torch_dtype": "float32",
45
+ "transformers_version": "4.40.2",
46
+ "tubelet_size": [
47
+ 2,
48
+ 16,
49
+ 16
50
+ ],
51
+ "video_size": [
52
+ 32,
53
+ 224,
54
+ 224
55
+ ]
56
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a6aef0ec4e103f946150aaf4727a4f1609300591b78fd50a20eed6757e0f625
3
+ size 354639992
preprocessor_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "offset",
12
+ "do_normalize",
13
+ "image_mean",
14
+ "image_std",
15
+ "return_tensors",
16
+ "data_format",
17
+ "input_data_format"
18
+ ],
19
+ "crop_size": {
20
+ "height": 224,
21
+ "width": 224
22
+ },
23
+ "do_center_crop": true,
24
+ "do_normalize": true,
25
+ "do_rescale": true,
26
+ "do_resize": true,
27
+ "image_mean": [
28
+ 0.5,
29
+ 0.5,
30
+ 0.5
31
+ ],
32
+ "image_processor_type": "VivitImageProcessor",
33
+ "image_std": [
34
+ 0.5,
35
+ 0.5,
36
+ 0.5
37
+ ],
38
+ "offset": true,
39
+ "resample": 2,
40
+ "rescale_factor": 0.00784313725490196,
41
+ "size": {
42
+ "shortest_edge": 224
43
+ }
44
+ }
runs/May11_05-54-19_c8b476f1f9fa/events.out.tfevents.1715406958.c8b476f1f9fa.1848.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d62c37c2404e222f3c39383afc930dc4a4f8fea9bd961bb30b01e1c1b4d26fc
3
+ size 8975
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0b1263f7d6a19b6357aa5ff83ae37d354716980128f1c0dcce6533c5f78fdce
3
+ size 5048