End of training
Browse files- README.md +69 -0
- config.json +48 -0
- model.safetensors +3 -0
- preprocessor_config.json +27 -0
- runs/Jul18_19-28-44_b1c03f885992/events.out.tfevents.1721330934.b1c03f885992.34.0 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: google/vivit-b-16x2-kinetics400
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- f1
|
9 |
+
- recall
|
10 |
+
- precision
|
11 |
+
model-index:
|
12 |
+
- name: vivit-b-16x2-kinetics400-finetuned-cremad
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/yassmenyoussef55-arete-global/huggingface/runs/4jineisc)
|
20 |
+
# vivit-b-16x2-kinetics400-finetuned-cremad
|
21 |
+
|
22 |
+
This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
|
23 |
+
It achieves the following results on the evaluation set:
|
24 |
+
- Loss: 1.1824
|
25 |
+
- Accuracy: 0.6575
|
26 |
+
- F1: 0.6595
|
27 |
+
- Recall: 0.6575
|
28 |
+
- Precision: 0.6676
|
29 |
+
|
30 |
+
## Model description
|
31 |
+
|
32 |
+
More information needed
|
33 |
+
|
34 |
+
## Intended uses & limitations
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Training and evaluation data
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training procedure
|
43 |
+
|
44 |
+
### Training hyperparameters
|
45 |
+
|
46 |
+
The following hyperparameters were used during training:
|
47 |
+
- learning_rate: 0.0001
|
48 |
+
- train_batch_size: 1
|
49 |
+
- eval_batch_size: 1
|
50 |
+
- seed: 42
|
51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
52 |
+
- lr_scheduler_type: linear
|
53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
54 |
+
- training_steps: 11906
|
55 |
+
|
56 |
+
### Training results
|
57 |
+
|
58 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
|
59 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:---------:|
|
60 |
+
| 1.54 | 0.5 | 5953 | 1.7615 | 0.4614 | 0.4420 | 0.4614 | 0.5095 |
|
61 |
+
| 0.7419 | 1.5 | 11906 | 1.1824 | 0.6575 | 0.6595 | 0.6575 | 0.6676 |
|
62 |
+
|
63 |
+
|
64 |
+
### Framework versions
|
65 |
+
|
66 |
+
- Transformers 4.42.3
|
67 |
+
- Pytorch 2.1.2
|
68 |
+
- Datasets 2.20.0
|
69 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "ANG",
|
12 |
+
"1": "DIS",
|
13 |
+
"2": "FEA",
|
14 |
+
"3": "HAP",
|
15 |
+
"4": "NEU",
|
16 |
+
"5": "SAD"
|
17 |
+
},
|
18 |
+
"image_size": 224,
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"ANG": 0,
|
23 |
+
"DIS": 1,
|
24 |
+
"FEA": 2,
|
25 |
+
"HAP": 3,
|
26 |
+
"NEU": 4,
|
27 |
+
"SAD": 5
|
28 |
+
},
|
29 |
+
"layer_norm_eps": 1e-06,
|
30 |
+
"model_type": "vivit",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_channels": 3,
|
33 |
+
"num_frames": 32,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"qkv_bias": true,
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.42.3",
|
38 |
+
"tubelet_size": [
|
39 |
+
2,
|
40 |
+
16,
|
41 |
+
16
|
42 |
+
],
|
43 |
+
"video_size": [
|
44 |
+
32,
|
45 |
+
224,
|
46 |
+
224
|
47 |
+
]
|
48 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8796b37db4e9de459a82660dfe69fd43259229f15e5b1a8750703b77ee3801bc
|
3 |
+
size 354627680
|
preprocessor_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
0.5,
|
12 |
+
0.5,
|
13 |
+
0.5
|
14 |
+
],
|
15 |
+
"image_processor_type": "VivitImageProcessor",
|
16 |
+
"image_std": [
|
17 |
+
0.5,
|
18 |
+
0.5,
|
19 |
+
0.5
|
20 |
+
],
|
21 |
+
"offset": true,
|
22 |
+
"resample": 2,
|
23 |
+
"rescale_factor": 0.00784313725490196,
|
24 |
+
"size": {
|
25 |
+
"shortest_edge": 224
|
26 |
+
}
|
27 |
+
}
|
runs/Jul18_19-28-44_b1c03f885992/events.out.tfevents.1721330934.b1c03f885992.34.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c92d7cf8bbdc49d26f3fdacf492b8b1c92bfcd763da75edc437f67b097fb4b99
|
3 |
+
size 257492
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c8fc3b22c9208deb77fa6c572b64be64627b3c515e034c8f51e94991d594a43
|
3 |
+
size 5176
|