Screenshots Detection To Classification

🚀 Screenshots_detection_to_classification

This model is a fine - tuned version of a base model for image classification and screenshots detection, achieving high accuracy on the evaluation set.

🚀 Quick Start

This model is a fine - tuned version of [google/vit - base - patch16 - 224](https://huggingface.co/google/vit - base - patch16 - 224) on the private_images_dataset dataset. It achieves the following results on the evaluation set:

• Loss: 0.1192
• Accuracy: 0.9881

✨ Features

• Fine - Tuned Model: Based on the [google/vit - base - patch16 - 224](https://huggingface.co/google/vit - base - patch16 - 224) model, fine - tuned for specific tasks.
• High Accuracy: Achieves an accuracy of 0.9881 on the evaluation set.

🔧 Technical Details

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0002
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
• lr_scheduler_type: linear
• num_epochs: 4

Framework versions

• Transformers 4.44.1
• Pytorch 2.4.0+cu118
• Datasets 2.21.0
• Tokenizers 0.19.1

📄 License

This project is licensed under the Apache - 2.0 license.