nguyenkhoa/dinov2_Liveness_detection_v2.2.1

<!-- 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. -->

<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>

dinov2Livenessdetection_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
• —trainbatchsize: 768
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —num_epochs: 5
• —mixedprecisiontraining: Native AMP

Training results

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