/vit_recognizer

VisionTransformerを使った画像認識Webアプリケーション

Primary LanguageJupyter Notebook

vit_recognizer

Image Recognition Web Application using Pretrained VisionTransformer

Demo

demo

Composition

.  
├── 📁 static  
│   ├── 📄 sample_image01.jpg  
│   ├── 📄 sample_image02.jpg  
│   └── 📄 sample_image03.jpg    
├── 📁 templates  
│   └── 📄 index.html 
├── 📄 app.py
├── 📄 labels_map.txt
└── 📄 vit.ipynb