# pytorch-flask-api

**Repository Path**: livion_i/pytorch-flask-api

## Basic Information

- **Project Name**: pytorch-flask-api
- **Description**: 使用flash 建立推理app 非常好用
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2022-11-10
- **Last Updated**: 2022-11-10

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# PyTorch Flask API

This repo contains a sample code to show how to create a Flask API server by deploying our PyTorch model. This is a sample code which goes with [tutorial](https://pytorch.org/tutorials/intermediate/flask_rest_api_tutorial.html).

If you'd like to learn how to deploy to Heroku, then check [this repo](https://github.com/avinassh/pytorch-flask-api-heroku).


## How to 

Install the dependencies:

    pip install -r requirements.txt


Run the Flask server:

    FLASK_ENV=development FLASK_APP=app.py flask run


From another tab, send the image file in a request:

    curl -X POST -F file=@cat_pic.jpeg http://localhost:5000/predict

## Deploy with Docker

Build image

    docker build --network=host -t pytorch_flask:v0 .

Run Docker

    docker run --name pytorch_flask -p 5000:5000 -v <your path>/pytorch-flask-api-master/:/docker_demo -d pytorch_flask:v0

send the image file in a request:

    curl -X POST -F file=@cat_pic.jpeg http://localhost:5000/predict

## License

The mighty MIT license. Please check `LICENSE` for more details.