Downloads · 30 days
28
15% of all-time downloads
dinov2_Liveness_detection_v2.2.1
nguyenkhoa/dinov2_Liveness_detection_v2.2.1
dinov2_Liveness_detection_v2.2.1 is a image classification model from nguyenkhoa. Use it when you need a label for an image. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
189
Public
Parameters
22.1M
2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors88.3 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- Model type
- dinov2
- Access
- Public
- Created
- Jan 14, 2025
- Updated
- Jan 23, 2025
- SHA
- dab24a56
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
dinov2_Liveness_detection_v2.2.1
This model is a fine-tuned version of nguyenkhoa/dinov2_Liveness_detection_v2.1.4 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0301
- Accuracy: 0.9910
- F1: 0.9910
- Recall: 0.9910
- Precision: 0.9910
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 768
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Recall | Precision |
|---|---|---|---|---|---|---|---|
| 0.4052 | 0.3232 | 64 | 0.0775 | 0.9712 | 0.9713 | 0.9712 | 0.9712 |
| 0.0784 | 0.6465 | 128 | 0.0545 | 0.9803 | 0.9803 | 0.9803 | 0.9804 |
| 0.0639 | 0.9697 | 192 | 0.0615 | 0.9771 | 0.9772 | 0.9771 | 0.9772 |
| 0.0479 | 1.2929 | 256 | 0.0572 | 0.9795 | 0.9794 | 0.9795 | 0.9800 |
| 0.0439 | 1.6162 | 320 | 0.0422 | 0.9844 | 0.9844 | 0.9844 | 0.9844 |
| 0.0392 | 1.9394 | 384 | 0.0564 | 0.9803 | 0.9801 | 0.9803 | 0.9810 |
| 0.0374 | 2.2626 | 448 | 0.0464 | 0.9837 | 0.9837 | 0.9837 | 0.9837 |
| 0.0273 | 2.5859 | 512 | 0.0378 | 0.9861 | 0.9861 | 0.9861 | 0.9861 |
| 0.0271 | 2.9091 | 576 | 0.0336 | 0.9883 | 0.9883 | 0.9883 | 0.9884 |
| 0.021 | 3.2323 | 640 | 0.0418 | 0.9859 | 0.9859 | 0.9859 | 0.9859 |
| 0.019 | 3.5556 | 704 | 0.0454 | 0.9848 | 0.9849 | 0.9848 | 0.9849 |
| 0.0177 | 3.8788 | 768 | 0.0359 | 0.9883 | 0.9883 | 0.9883 | 0.9883 |
| 0.0134 | 4.2020 | 832 | 0.0410 | 0.9874 | 0.9874 | 0.9874 | 0.9877 |
| 0.0102 | 4.5253 | 896 | 0.0314 | 0.9910 | 0.9910 | 0.9910 | 0.9910 |
| 0.0103 | 4.8485 | 960 | 0.0301 | 0.9910 | 0.9910 | 0.9910 | 0.9910 |
Evaluate results
- Accuracy: 0.8626
- F1: 0.8909
- Recall: 0.9924
- Precision: 0.6903
- APCER: 0.1940
- BPCER: 0.0076
- ACER: 0.1008
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Image Classification
- Library
- transformers
- Type
- dinov2
- Created
- Jan 14, 2025
- Updated
- Jan 23, 2025