batch-size16_FFPP-c23_ffmpeg-1FPS-qv1_faces-expand0-aligned_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: 0.1590
- Accuracy: 0.9342
- Precision: 0.9457
- Recall: 0.9716
- F1: 0.9585
- Roc Auc: 0.9778
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
---|---|---|---|---|---|---|---|---|
0.2014 | 1.0 | 1344 | 0.1590 | 0.9342 | 0.9457 | 0.9716 | 0.9585 | 0.9778 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.3.0
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 6
Finetuned from
Evaluation results
- Accuracy on imagefoldertest set self-reported0.934
- Precision on imagefoldertest set self-reported0.946
- Recall on imagefoldertest set self-reported0.972
- F1 on imagefoldertest set self-reported0.958