ViaResto

ViaResto is a website developed by ViaRézo for monitoring the waiting time in CROUS restaurants.

Installation

Use the template files in ./backend and ./frontend to define the configuration and environment variables.

In development mode

Run the backend server

Start the mysql container
docker run -p 3306:3306 --env-file .env -d mysql:latest mysqld --default-authentication-plugin=mysql_native_password
Build and start the tensorflow/serving container
docker build -t model -f ./Dockerfile-model . && docker run -p 8501:8501 --env MODEL_NAME=model -d model
Form ./backend, install the dependencies by executing pip install -r requirements.txt and run directly the uvicorn server :
python -m uvicorn main:app --reload --port=3001 --host 0.0.0.0.

Run the frontend server

Open a new terminal and run :

$ cd frontend
$ npm install
$ npm start

In production mode

From /backend execute docker-compose build && docker-compose up -d.
From /frontend run npm run build and serve the build generated.

Linting

So the new commits can be deployed, you need to use the linter for the backend and the frontend.
To lint the backend code, run pycodestyle --config=./setup.cnf ./backend. To fix the errors, you can use autoformat with autopep8 running autopep8 --in-place --global-config=./setup.cnf --recursive --aggressive ./. If you use a virtual environment called env/ you should add --exclude=./env in both command so the linter ignore the folder.
To lint the frontend, run npm run lint. You can fix most of the errors using npm run format.

Contributing

If you would like to contribute, contact us at support@ml.viarezo.fr.

License

The project doesn't have any license. However, the crowd-counting AI model used is based on this repository: https://github.com/ZhengPeng7/W-Net-Keras. The dataset used is ShanghaiTech Part B. The model is given a 3-channel image and generates a density map of half the size of the input image. The estimated number of people is obtained by summing on all pixels of the density map.