Training in progress, epoch 0
Browse files- config.json +38 -0
- model.safetensors +3 -0
- preprocessor_config.json +42 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/timesformer-base-finetuned-k400",
|
3 |
+
"architectures": [
|
4 |
+
"TimesformerForVideoClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.0,
|
7 |
+
"attention_type": "divided_space_time",
|
8 |
+
"drop_path_rate": 0,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "360",
|
14 |
+
"1": "cutback-frontside",
|
15 |
+
"2": "roller",
|
16 |
+
"3": "take-off"
|
17 |
+
},
|
18 |
+
"image_size": 224,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"360": 0,
|
23 |
+
"cutback-frontside": 1,
|
24 |
+
"roller": 2,
|
25 |
+
"take-off": 3
|
26 |
+
},
|
27 |
+
"layer_norm_eps": 1e-06,
|
28 |
+
"model_type": "timesformer",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_channels": 3,
|
31 |
+
"num_frames": 8,
|
32 |
+
"num_hidden_layers": 12,
|
33 |
+
"patch_size": 16,
|
34 |
+
"problem_type": "single_label_classification",
|
35 |
+
"qkv_bias": true,
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.41.2"
|
38 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab0875b31e0fb047b3dd111ffc3179313be5aab4bbd5c39db4aa75f1ca679d6a
|
3 |
+
size 485078408
|
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:bab492c38d4e063b93f84f8f2a1e48e2119198270a2fddd2ea694455e41858b1
|
3 |
+
size 5112
|