hchcsuim's picture
Model save
4192137 verified
metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: FFPP-Raw_1FPS_faces-expand-40-aligned_val-ds-celeb-df
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7452239273410586

FFPP-Raw_1FPS_faces-expand-40-aligned_val-ds-celeb-df

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: 0.6364
  • Accuracy: 0.7452

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
0.1559 1.0 1348 0.5716 0.7123
0.1238 2.0 2696 0.4573 0.7972
0.0687 3.0 4044 0.6364 0.7452

Framework versions

  • Transformers 4.39.2
  • Pytorch 2.2.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2