Skip to content

Latest commit

 

History

History
47 lines (27 loc) · 1.34 KB

README.md

File metadata and controls

47 lines (27 loc) · 1.34 KB
Raw

Dog Breed Identifier using tensorflow image classification.

Dataset used: Stanford Dogs Dataset

I've also used other images for extra dog breeds. I will create a link to a google drive featuring the latest built models.

Technologies

FARM Stack

  • FastAPI
  • React
  • MongoDB

+ Other

  • Tensorflow 2.15
  • TypeScript
  • Vite.js

Installation

Docker Compose

docker compose up

This is the only command needed to run the application locally, apart from the model itself.

Local

If you don't have docker installed or want to use docker, you can run these commands instead. Before running the backend though, you will need to change each of the imports from from backend import... to import ....

cd backend

pip install -r ../requirements.txt

uvicorn main:app --reload

If you wish to use your GPU to build the model yourself, please follow this guide.

cd frontend

npm install

npm run dev

Other

I haven't uploaded the model itself since there seems to be a bug with git lfs, when downloaded the model is corrupted. In backend, create a folder named model and insert the model from this google drive download link.