maurorisonho/vit-beans-computer-vision

Vision Transformer (ViT) Fine-Tuned on Beans (Computer Vision Course)

This model is a fine-tuned Vision Transformer (ViT-Base) on the Beans dataset for automated crop disease diagnosis, developed for the Hugging Face Computer Vision Course.

🚀 Model Details

• —Architecture: Vision Transformer vit-base-patch16-224
• —Dataset: Beans (Angular Leaf Spot, Bean Rust, Healthy)
• —Validation Accuracy: 98.5%
• —Framework: PyTorch & Hugging Face Transformers