FFPP-Raw_1FPS_faces-expand-40-aligned_metric
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: 0.4464
- Accuracy: 0.8065
- Recall: 0.5993
- Precision: 0.2691
- F1: 0.3714
- Roc Auc: 0.8135
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: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | Precision | F1 | Roc Auc |
---|---|---|---|---|---|---|---|---|
0.1821 | 1.0 | 1348 | 0.1286 | 0.9464 | 0.8533 | 0.8953 | 0.8738 | 0.9858 |
0.1333 | 2.0 | 2696 | 0.0715 | 0.9725 | 0.9129 | 0.9586 | 0.9352 | 0.9960 |
0.0809 | 3.0 | 4044 | 0.0520 | 0.9804 | 0.9344 | 0.9743 | 0.9539 | 0.9980 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.2.2
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for hchcsuim/FFPP-Raw_1FPS_faces-expand-40-aligned_metric
Base model
microsoft/swin-tiny-patch4-window7-224
Finetuned
this model
Evaluation results
- Accuracy on imagefolderself-reported0.806
- Recall on imagefolderself-reported0.599
- Precision on imagefolderself-reported0.269
- F1 on imagefolderself-reported0.371