lucataco/watermark_detector

amrul-hzz's fine-tuned version of vit-base-patch16-224-in21k for watermark image detection

  • Public
  • 84 runs

Run time and cost

This model runs on CPU hardware. Predictions typically complete within 90 seconds.

Readme

This is a Cog Implementation of amrul-hzz/watermark_detector

watermark_detector

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6014 - Accuracy: 0.6574

Training hyperparameters

The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.6492 1.0 1139 0.6375 0.6262
0.6172 2.0 2278 0.6253 0.6438
0.578 3.0 3417 0.6110 0.6508

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3