JackWong0911
commited on
End of training
Browse files- README.md +49 -0
- config.json +39 -0
- model.safetensors +3 -0
- preprocessor_config.json +26 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-4.0
|
3 |
+
base_model: facebook/timesformer-base-finetuned-k400
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: timesformer-base-finetuned-k400-kinetic400-subset-epoch6-num_frame_10_myViT2window3_more_data_b4
|
8 |
+
results: []
|
9 |
+
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
# timesformer-base-finetuned-k400-kinetic400-subset-epoch6-num_frame_10_myViT2window3_more_data_b4
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k400](https://huggingface.co/facebook/timesformer-base-finetuned-k400) on an unknown dataset.
|
17 |
+
|
18 |
+
## Model description
|
19 |
+
|
20 |
+
More information needed
|
21 |
+
|
22 |
+
## Intended uses & limitations
|
23 |
+
|
24 |
+
More information needed
|
25 |
+
|
26 |
+
## Training and evaluation data
|
27 |
+
|
28 |
+
More information needed
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
### Training hyperparameters
|
33 |
+
|
34 |
+
The following hyperparameters were used during training:
|
35 |
+
- learning_rate: 5e-05
|
36 |
+
- train_batch_size: 4
|
37 |
+
- eval_batch_size: 4
|
38 |
+
- seed: 42
|
39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
+
- lr_scheduler_type: linear
|
41 |
+
- lr_scheduler_warmup_ratio: 0.1
|
42 |
+
- training_steps: 72
|
43 |
+
|
44 |
+
### Framework versions
|
45 |
+
|
46 |
+
- Transformers 4.38.2
|
47 |
+
- Pytorch 2.1.0+cu121
|
48 |
+
- Datasets 2.19.0
|
49 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/timesformer-base-finetuned-k400",
|
3 |
+
"architectures": [
|
4 |
+
"MyTimesformerForVideoClassification"
|
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": "archery",
|
14 |
+
"1": "bowling",
|
15 |
+
"2": "flying_kite",
|
16 |
+
"3": "high_jump",
|
17 |
+
"4": "marching"
|
18 |
+
},
|
19 |
+
"image_size": 224,
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
+
"label2id": {
|
23 |
+
"archery": 0,
|
24 |
+
"bowling": 1,
|
25 |
+
"flying_kite": 2,
|
26 |
+
"high_jump": 3,
|
27 |
+
"marching": 4
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-06,
|
30 |
+
"model_type": "timesformer",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_channels": 3,
|
33 |
+
"num_frames": 10,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"patch_size": 16,
|
36 |
+
"qkv_bias": true,
|
37 |
+
"torch_dtype": "float32",
|
38 |
+
"transformers_version": "4.38.2"
|
39 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:730f6df77c65aedc812b011a72640d9a25929a5db905dbb0abc1e16de85b9a77
|
3 |
+
size 485087636
|
preprocessor_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"crop_size": {
|
3 |
+
"height": 224,
|
4 |
+
"width": 224
|
5 |
+
},
|
6 |
+
"do_center_crop": true,
|
7 |
+
"do_normalize": true,
|
8 |
+
"do_rescale": true,
|
9 |
+
"do_resize": true,
|
10 |
+
"image_mean": [
|
11 |
+
0.485,
|
12 |
+
0.456,
|
13 |
+
0.406
|
14 |
+
],
|
15 |
+
"image_processor_type": "VideoMAEImageProcessor",
|
16 |
+
"image_std": [
|
17 |
+
0.229,
|
18 |
+
0.224,
|
19 |
+
0.225
|
20 |
+
],
|
21 |
+
"resample": 2,
|
22 |
+
"rescale_factor": 0.00392156862745098,
|
23 |
+
"size": {
|
24 |
+
"shortest_edge": 224
|
25 |
+
}
|
26 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4517c95c1edd79a9c3c6edcab716382cf97ff16862d8c2123e3176bde559f65c
|
3 |
+
size 5048
|