Skip to content

Latest commit

 

History

History
33 lines (24 loc) · 854 Bytes

README.md

File metadata and controls

33 lines (24 loc) · 854 Bytes

70 Dog Breed Classification

This is a Next.js app that classifies 70 different dog breeds, trained with Efficient Net B0, achieved ~90% accuracy.

The model is trained using PyTorch, can be viewed in /pytorch-training folder.

After training, the model is saved as ONNX format. The model is loaded and inferenced on edge using ONNX Runtime Web API, thus has a low edge inference time.

Tech Used

WebApp

  • Next.js
  • Tailwind
  • ONNX Runtime Web API
  • Edge Inference

Machine Learning Model

  • PyTorch
  • ResNet18 and EffNet B0
  • Kaggle Dataset - here

Getting Started

First, run the development server:

npm run dev
# or
yarn dev
# or
pnpm dev

Open http://localhost:3000 with your browser to see the result.