Edit model card

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

swin-tiny-patch4-window7-224-uploads-classifier

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: 0.0740
  • Accuracy: 0.9669

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: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy
1.57 0.99 17 1.0733 0.7355
0.5726 1.97 34 0.4882 0.8347
0.213 2.96 51 0.1166 0.9628
0.1528 4.0 69 0.1640 0.9339
0.1243 4.99 86 0.1529 0.9380
0.0985 5.97 103 0.1888 0.9215
0.0838 6.96 120 0.1224 0.9421
0.0667 8.0 138 0.1046 0.9421
0.0455 8.99 155 0.0740 0.9669
0.0469 9.97 172 0.0781 0.9669
0.0472 10.96 189 0.1143 0.9628
0.0378 12.0 207 0.1974 0.9545
0.0386 12.99 224 0.1051 0.9587
0.035 13.97 241 0.0719 0.9545
0.0339 14.96 258 0.1225 0.9504
0.0292 16.0 276 0.0962 0.9587
0.0278 16.99 293 0.1322 0.9463
0.0233 17.97 310 0.1064 0.9545
0.028 18.96 327 0.1207 0.9504
0.0269 19.71 340 0.1161 0.9504

Framework versions

  • Transformers 4.28.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
0
Inference Examples
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.

Evaluation results