https://github.com/devdezzies/foodmini-vit

FoodMini is an image recognition model trained on subset of FoodVision 101 dataset consisting of three labels (sushi, pizza, and steak). This project implements ViT (Vision Transformer) from its original research paper as state-of-the-art image recognition model.
https://github.com/devdezzies/foodmini-vit

computer-vision image-recognition paper-implementations pytorch transformer vision-transformer

Last synced: about 3 hours ago
JSON representation

FoodMini is an image recognition model trained on subset of FoodVision 101 dataset consisting of three labels (sushi, pizza, and steak). This project implements ViT (Vision Transformer) from its original research paper as state-of-the-art image recognition model.

• Host: GitHub
• URL: https://github.com/devdezzies/foodmini-vit
• Owner: devdezzies
• Created: 2024-08-25T12:33:22.000Z (about 1 month ago)
• Default Branch: main
• Last Pushed: 2024-08-27T13:00:07.000Z (about 1 month ago)
• Last Synced: 2024-09-22T06:02:14.645Z (5 days ago)
• Topics: computer-vision, image-recognition, paper-implementations, pytorch, transformer, vision-transformer
• Language: Jupyter Notebook
• Homepage: https://arxiv.org/abs/2010.11929
• Size: 35.3 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README