https://github.com/tuvovan/ml_in_production

A set of demo of deploying a Machine Learning Model in production using various methods
https://github.com/tuvovan/ml_in_production

deep-learning docker fastapi machine-learning mlops nginx rest-api tfserving uwsgi-nginx-docker

Last synced: about 1 month ago
JSON representation

A set of demo of deploying a Machine Learning Model in production using various methods

• Host: GitHub
• URL: https://github.com/tuvovan/ml_in_production
• Owner: tuvovan
• Created: 2021-09-22T02:19:57.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2021-09-22T03:37:12.000Z (over 3 years ago)
• Last Synced: 2023-05-18T09:27:07.065Z (over 1 year ago)
• Topics: deep-learning, docker, fastapi, machine-learning, mlops, nginx, rest-api, tfserving, uwsgi-nginx-docker
• Language: Python
• Homepage:
• Size: 89.4 MB
• Stars: 55
• Watchers: 1
• Forks: 21
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Machine Learning Model in Production

This git is for those who have concern about serving your machine learning model to production.

## Overview

The tutorial will show you how to deploy your Tensorflow (Keras) model (specifically ResNet50 pretrained on Imagenet) using:

- [RestAPI + Redis](https://github.com/tuvovan/ml_in_production/tree/master/restAPI)

- [RestAPI + nginx + uwsgi](https://github.com/tuvovan/ml_in_production/tree/master/nginx_uwsgi)

- [FastAPI + Docker](https://github.com/tuvovan/ml_in_production/tree/master/fastAPI)

- [RestAPI + Kubernetes + Docker](https://github.com/tuvovan/ml_in_production/tree/master/py_flask_ml_score_api)

- [Tensorflow Serving](https://github.com/tuvovan/ml_in_production/tree/master/tfserving)

_**Note**: This git is the my collected knowledge during my on-going journey to this interesting part of Machine Learning, so there will be some mistakes or misunderstanding. For those who detect any faults, send me a pull request and contribute!_

## How to use

Each method will be in each different folder with its corresponding Readme file.

## Acknowledgement

Those methods are what I found on the internet with a thorough check and run test on my Mac. Things maybe different on each computer and operation system.

If you hit any problem when you try to run any of those methods, leave a issue and I will get back shortly.