Hugging Face's logo

mitegvg
/
videomae-tiny-92-kinetics-binary-finetuned-xd-violence

Video Classification
Transformers
TensorBoard
Safetensors
videomae
Generated from Trainer
Model card Files
xet
 Metrics Community
mitegvg commited on
Commit
f3eeaa6
·
verified ·
1 Parent(s): 2e64de7

Training in progress, epoch 22

Browse files
Files changed (9) hide show
  1. README.md +102 -0
  2. config.json +39 -0
  3. model.safetensors +3 -0
  4. preprocessor_config.json +26 -0
  5. runs/Nov01_08-37-09_DESKTOP-JCNIME4/events.out.tfevents.1761986235.DESKTOP-JCNIME4.11508.0 +3 -0
  6. runs/Nov01_11-09-44_DESKTOP-JCNIME4/events.out.tfevents.1761995390.DESKTOP-JCNIME4.5968.0 +3 -0
  7. runs/Sep28_13-06-21_DESKTOP-JCNIME4/events.out.tfevents.1759061184.DESKTOP-JCNIME4.464.0 +3 -0
  8. runs/Sep28_13-08-14_DESKTOP-JCNIME4/events.out.tfevents.1759061295.DESKTOP-JCNIME4.464.1 +3 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: MCG-NJU/videomae-base-finetuned-kinetics
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ - precision
10
+ - recall
11
+ - f1
12
+ model-index:
13
+ - name: videomae-tiny-ssv2-binary-finetuned-xd-violence
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # videomae-tiny-ssv2-binary-finetuned-xd-violence
21
+
22
+ This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on an unknown dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.6274
25
+ - Accuracy: 0.6535
26
+ - Precision: 0.72
27
+ - Recall: 0.5575
28
+ - F1: 0.6284
29
+ - Tp: 126
30
+ - Tn: 155
31
+ - Fp: 49
32
+ - Fn: 100
33
+ - Specificity: 0.7598
34
+ - Unsafe Precision At Default Threshold: 0.5561
35
+ - Unsafe Recall At Default Threshold: 0.9425
36
+ - Unsafe F1 At Default Threshold: 0.6995
37
+ - Unsafe Precision At Best Threshold: 0.5561
38
+ - Unsafe Recall At Best Threshold: 0.9425
39
+ - Unsafe Fbeta At Best Threshold: 0.8275
40
+ - Best Threshold: 0.25
41
+ - Roc Auc: 0.7261
42
+ - Average Precision: 0.7410
43
+
44
+ ## Model description
45
+
46
+ More information needed
47
+
48
+ ## Intended uses & limitations
49
+
50
+ More information needed
51
+
52
+ ## Training and evaluation data
53
+
54
+ More information needed
55
+
56
+ ## Training procedure
57
+
58
+ ### Training hyperparameters
59
+
60
+ The following hyperparameters were used during training:
61
+ - learning_rate: 5e-05
62
+ - train_batch_size: 8
63
+ - eval_batch_size: 8
64
+ - seed: 42
65
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
66
+ - lr_scheduler_type: cosine
67
+ - lr_scheduler_warmup_ratio: 0.1
68
+ - num_epochs: 20
69
+ - mixed_precision_training: Native AMP
70
+
71
+ ### Training results
72
+
73
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Tp | Tn | Fp | Fn | Specificity | Unsafe Precision At Default Threshold | Unsafe Recall At Default Threshold | Unsafe F1 At Default Threshold | Unsafe Precision At Best Threshold | Unsafe Recall At Best Threshold | Unsafe Fbeta At Best Threshold | Best Threshold | Roc Auc | Average Precision |
74
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:---:|:---:|:---:|:---:|:-----------:|:-------------------------------------:|:----------------------------------:|:------------------------------:|:----------------------------------:|:-------------------------------:|:------------------------------:|:--------------:|:-------:|:-----------------:|
75
+ | 0.715 | 1.0 | 422 | 0.7038 | 0.5349 | 0.5428 | 0.7301 | 0.6226 | 165 | 65 | 139 | 61 | 0.3186 | 0.5293 | 1.0 | 0.6922 | 0.5293 | 1.0 | 0.8490 | 0.25 | 0.5644 | 0.5972 |
76
+ | 0.6737 | 2.0 | 844 | 0.6732 | 0.5860 | 0.6333 | 0.5044 | 0.5616 | 114 | 138 | 66 | 112 | 0.6765 | 0.5293 | 1.0 | 0.6922 | 0.5398 | 0.9912 | 0.8491 | 0.3 | 0.6353 | 0.6177 |
77
+ | 0.6639 | 3.0 | 1266 | 0.6413 | 0.6256 | 0.6923 | 0.5177 | 0.5924 | 117 | 152 | 52 | 109 | 0.7451 | 0.5396 | 0.9956 | 0.6998 | 0.5396 | 0.9956 | 0.8516 | 0.25 | 0.7109 | 0.7115 |
78
+ | 0.7136 | 4.0 | 1688 | 0.6424 | 0.6581 | 0.7283 | 0.5575 | 0.6316 | 126 | 157 | 47 | 100 | 0.7696 | 0.5305 | 1.0 | 0.6933 | 0.5437 | 0.9912 | 0.8511 | 0.3 | 0.7135 | 0.7143 |
79
+ | 0.6542 | 5.0 | 2110 | 0.6289 | 0.6767 | 0.6605 | 0.7920 | 0.7203 | 179 | 112 | 92 | 47 | 0.5490 | 0.5280 | 1.0 | 0.6911 | 0.5383 | 0.9956 | 0.8510 | 0.325 | 0.7326 | 0.7281 |
80
+ | 0.64 | 6.0 | 2532 | 0.6257 | 0.6605 | 0.7326 | 0.5575 | 0.6332 | 126 | 158 | 46 | 100 | 0.7745 | 0.5463 | 0.9912 | 0.7044 | 0.5463 | 0.9912 | 0.8524 | 0.25 | 0.7230 | 0.7415 |
81
+ | 0.5858 | 7.0 | 2954 | 0.6348 | 0.6581 | 0.7687 | 0.5 | 0.6059 | 113 | 170 | 34 | 113 | 0.8333 | 0.6109 | 0.8894 | 0.7243 | 0.6109 | 0.8894 | 0.8151 | 0.25 | 0.7312 | 0.7420 |
82
+ | 0.6228 | 8.0 | 3376 | 0.6220 | 0.6698 | 0.7234 | 0.6018 | 0.6570 | 136 | 152 | 52 | 90 | 0.7451 | 0.5606 | 0.9823 | 0.7138 | 0.5606 | 0.9823 | 0.8538 | 0.25 | 0.7356 | 0.7342 |
83
+ | 0.6999 | 9.0 | 3798 | 0.6204 | 0.6698 | 0.6944 | 0.6637 | 0.6787 | 150 | 138 | 66 | 76 | 0.6765 | 0.5343 | 1.0 | 0.6965 | 0.5450 | 0.9912 | 0.8517 | 0.3 | 0.7298 | 0.7371 |
84
+ | 0.6338 | 10.0 | 4220 | 0.6270 | 0.6791 | 0.6803 | 0.7345 | 0.7064 | 166 | 126 | 78 | 60 | 0.6176 | 0.5319 | 0.9956 | 0.6934 | 0.5493 | 0.9867 | 0.8511 | 0.325 | 0.7254 | 0.7254 |
85
+ | 0.6303 | 11.0 | 4642 | 0.6278 | 0.6744 | 0.6886 | 0.6947 | 0.6916 | 157 | 133 | 71 | 69 | 0.6520 | 0.5493 | 0.9867 | 0.7057 | 0.5493 | 0.9867 | 0.8511 | 0.25 | 0.7191 | 0.7243 |
86
+ | 0.5972 | 12.0 | 5064 | 0.6289 | 0.6442 | 0.6834 | 0.6018 | 0.64 | 136 | 141 | 63 | 90 | 0.6912 | 0.5479 | 0.9867 | 0.7046 | 0.5479 | 0.9867 | 0.8505 | 0.25 | 0.7192 | 0.7258 |
87
+ | 0.6028 | 13.0 | 5486 | 0.6168 | 0.6605 | 0.7128 | 0.5929 | 0.6473 | 134 | 150 | 54 | 92 | 0.7353 | 0.5461 | 0.9690 | 0.6986 | 0.5662 | 0.9646 | 0.8456 | 0.275 | 0.7372 | 0.7486 |
88
+ | 0.6118 | 14.0 | 5908 | 0.6310 | 0.6349 | 0.7197 | 0.5 | 0.5901 | 113 | 160 | 44 | 113 | 0.7843 | 0.5646 | 0.9469 | 0.7074 | 0.5646 | 0.9469 | 0.8340 | 0.25 | 0.7263 | 0.7392 |
89
+ | 0.6541 | 15.0 | 6330 | 0.6237 | 0.6419 | 0.7022 | 0.5531 | 0.6188 | 125 | 151 | 53 | 101 | 0.7402 | 0.5473 | 0.9735 | 0.7006 | 0.5651 | 0.9602 | 0.8424 | 0.275 | 0.7271 | 0.7365 |
90
+ | 0.5885 | 16.0 | 6752 | 0.6265 | 0.6628 | 0.7396 | 0.5531 | 0.6329 | 125 | 160 | 44 | 101 | 0.7843 | 0.5556 | 0.9735 | 0.7074 | 0.5556 | 0.9735 | 0.8462 | 0.25 | 0.7241 | 0.7418 |
91
+ | 0.5378 | 17.0 | 7174 | 0.6252 | 0.6512 | 0.7135 | 0.5619 | 0.6287 | 127 | 153 | 51 | 99 | 0.75 | 0.5561 | 0.9646 | 0.7055 | 0.5561 | 0.9646 | 0.8410 | 0.25 | 0.7244 | 0.7396 |
92
+ | 0.6367 | 18.0 | 7596 | 0.6248 | 0.6581 | 0.7135 | 0.5841 | 0.6423 | 132 | 151 | 53 | 94 | 0.7402 | 0.5553 | 0.9558 | 0.7024 | 0.5553 | 0.9558 | 0.8353 | 0.25 | 0.7268 | 0.7411 |
93
+ | 0.6296 | 19.0 | 8018 | 0.6264 | 0.6535 | 0.72 | 0.5575 | 0.6284 | 126 | 155 | 49 | 100 | 0.7598 | 0.5573 | 0.9469 | 0.7016 | 0.5573 | 0.9469 | 0.8307 | 0.25 | 0.7266 | 0.7412 |
94
+ | 0.6629 | 20.0 | 8440 | 0.6274 | 0.6535 | 0.72 | 0.5575 | 0.6284 | 126 | 155 | 49 | 100 | 0.7598 | 0.5561 | 0.9425 | 0.6995 | 0.5561 | 0.9425 | 0.8275 | 0.25 | 0.7261 | 0.7410 |
95
+
96
+
97
+ ### Framework versions
98
+
99
+ - Transformers 4.51.3
100
+ - Pytorch 2.1.0+cu118
101
+ - Datasets 3.6.0
102
+ - Tokenizers 0.21.4
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VideoMAEForVideoClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.0,
6
+ "decoder_hidden_size": 384,
7
+ "decoder_intermediate_size": 1536,
8
+ "decoder_num_attention_heads": 6,
9
+ "decoder_num_hidden_layers": 4,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.0,
12
+ "hidden_size": 192,
13
+ "id2label": {
14
+ "0": "safe",
15
+ "1": "unsafe"
16
+ },
17
+ "image_size": 224,
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 768,
20
+ "label2id": {
21
+ "safe": 0,
22
+ "unsafe": 1
23
+ },
24
+ "layer_norm_eps": 1e-12,
25
+ "mask_ratio": 0.0,
26
+ "model_type": "videomae",
27
+ "norm_pix_loss": true,
28
+ "num_attention_heads": 3,
29
+ "num_channels": 3,
30
+ "num_frames": 16,
31
+ "num_hidden_layers": 12,
32
+ "patch_size": 16,
33
+ "problem_type": "single_label_classification",
34
+ "qkv_bias": true,
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.51.3",
37
+ "tubelet_size": 2,
38
+ "use_mean_pooling": true
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5db5ac579ccceabd21a1e6dd46ccff9a57a50c90f227926357335da70fb9e676
3
+ size 22549696
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
+ }
runs/Nov01_08-37-09_DESKTOP-JCNIME4/events.out.tfevents.1761986235.DESKTOP-JCNIME4.11508.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2cad2f2008cb01a0eccec96816d00395d44a2aa18ee44b960a4f1fe56967148
3
+ size 10177
runs/Nov01_11-09-44_DESKTOP-JCNIME4/events.out.tfevents.1761995390.DESKTOP-JCNIME4.5968.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:588164d3ff81d93b5ea9e51cc31daff7d76f69efed83a138be9807a117f5c84a
3
+ size 25730
runs/Sep28_13-06-21_DESKTOP-JCNIME4/events.out.tfevents.1759061184.DESKTOP-JCNIME4.464.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:704e4be8efda4ab69fb854c4c12602f6782ac5987719b4e2c640013b1d72c2ce
3
+ size 5303
runs/Sep28_13-08-14_DESKTOP-JCNIME4/events.out.tfevents.1759061295.DESKTOP-JCNIME4.464.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83b13ad812f6f3863112542210a41e87f733087993031516284847b3d17658a4
3
+ size 210513
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df4207392652e9aa256484f2d162291d5859c5c4517c328e364f29307469f411
3
+ size 5432