About This Project
A Vision Transformer fine-tuned on the Stanford Dogs dataset for 120-class breed classification. The model is deployed as a Gradio app on Hugging Face Spaces, where users can upload a photo and view the top predicted breeds with confidence scores.
Key Features
- ViT fine-tuning on Stanford Dogs
- 120-class breed classification
- Gradio app on Hugging Face Spaces
Technologies
PyTorchComputer VisionHugging Face