batch-size16_DFDC_opencv-1FPS_faces-expand40-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: 0.0521
- Accuracy: 0.9798
- Precision: 0.9849
- Recall: 0.9912
- F1: 0.9880
- Roc Auc: 0.9966
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 |
|---|---|---|---|---|---|---|---|---|
| 0.0861 | 1.0000 | 18506 | 0.0521 | 0.9798 | 0.9849 | 0.9912 | 0.9880 | 0.9966 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 219
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
Model tree for hchcsuim/batch-size16_DFDC_opencv-1FPS_faces-expand40-aligned_unaugmentation
Base model
microsoft/swin-tiny-patch4-window7-224Evaluation results
- Accuracy on imagefoldertest set self-reported0.980
- Precision on imagefoldertest set self-reported0.985
- Recall on imagefoldertest set self-reported0.991
- F1 on imagefoldertest set self-reported0.988