batch-size16_Celeb-DF_opencv-1FPS_unaugmentation
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3814
- Accuracy: 0.8482
- Precision: 0.8504
- Recall: 0.9931
- F1: 0.9162
- Roc Auc: 0.7709
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Roc Auc |
---|---|---|---|---|---|---|---|---|
0.4011 | 0.9951 | 101 | 0.3814 | 0.8482 | 0.8504 | 0.9931 | 0.9162 | 0.7709 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Finetuned from
Evaluation results
- Accuracy on imagefoldertest set self-reported0.848
- Precision on imagefoldertest set self-reported0.850
- Recall on imagefoldertest set self-reported0.993
- F1 on imagefoldertest set self-reported0.916