CarolLiu999 commited on
Commit
3657f1a
1 Parent(s): ff4364c

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/vivit-b-16x2",
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": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8"
20
+ },
21
+ "image_size": 224,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "LABEL_0": 0,
26
+ "LABEL_1": 1,
27
+ "LABEL_2": 2,
28
+ "LABEL_3": 3,
29
+ "LABEL_4": 4,
30
+ "LABEL_5": 5,
31
+ "LABEL_6": 6,
32
+ "LABEL_7": 7,
33
+ "LABEL_8": 8
34
+ },
35
+ "layer_norm_eps": 1e-06,
36
+ "model_type": "vivit",
37
+ "num_attention_heads": 12,
38
+ "num_channels": 3,
39
+ "num_frames": 32,
40
+ "num_hidden_layers": 12,
41
+ "qkv_bias": true,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.39.1",
44
+ "tubelet_size": [
45
+ 2,
46
+ 16,
47
+ 16
48
+ ]
49
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f3ba5b9e752f6009586d4098169c8812cb6584608e8346d14457df6ac003c4
3
+ size 354636908
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43c01fef88afccdc528255aea806d4297a92b28ff4850bbcec3dee74b85c1546
3
+ size 709393850
preprocessor_config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
25
+ "do_rescale": true,
26
+ "do_resize": true,
27
+ "do_zero_centering": true,
28
+ "image_mean": [
29
+ 0.5,
30
+ 0.5,
31
+ 0.5
32
+ ],
33
+ "image_processor_type": "VivitImageProcessor",
34
+ "image_std": [
35
+ 0.5,
36
+ 0.5,
37
+ 0.5
38
+ ],
39
+ "offset": true,
40
+ "resample": 2,
41
+ "rescale_factor": 0.00784313725490196,
42
+ "size": {
43
+ "shortest_edge": 256
44
+ }
45
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c44141bbdc09951afac7e1120c543329e05011264f0246580d2c7b808a155c7
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9284990f66d03fc74e49709815b6404578cc3ba340052062f101beebd4d2a1de
3
+ size 1064
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7cf22aa91e0592ff558e77c5f2529db433e25f76dc8ff80e4cc499dabd6c90b
3
+ size 4856