Alex-VisTas's picture
update model card README.md
2695f21
|
raw
history blame
2.14 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swin-tiny-patch4-window7-224-finetuned-woody
    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: 0.7321212121212122

swin-tiny-patch4-window7-224-finetuned-woody

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: 0.5392
  • Accuracy: 0.7321

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: 6

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.574 1.0 58 0.5392 0.7321
0.5784 2.0 116 0.5392 0.7321
0.5476 3.0 174 0.5392 0.7321
0.5571 4.0 232 0.5392 0.7321
0.5577 5.0 290 0.5392 0.7321
0.5625 6.0 348 0.5392 0.7321

Framework versions

  • Transformers 4.23.1
  • Pytorch 1.12.1+cu113
  • Datasets 2.5.2
  • Tokenizers 0.13.1