dnguyenngoc/ml-models-in-production
This repo gives an introduction to how to make full working example to serve your model using asynchronous Celery tasks and FastAPI. 🔥 🔥 🔥 🔥
This project helps machine learning engineers deploy their trained models as web services. It takes a pre-trained ML model and outputs a fully functional web application that can receive images, process them with the model, and return the predictions. This is ideal for developers or MLOps engineers who need to make their models accessible via an API and a web interface.
No commits in the last 6 months.
Use this if you are a developer looking for a template to serve your own machine learning models using FastAPI and Celery.
Not ideal if you are looking for an off-the-shelf solution without writing any code or if you need to train a model.
Stars
30
Forks
14
Language
Python
License
—
Category
Last pushed
May 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dnguyenngoc/ml-models-in-production"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
eightBEC/fastapi-ml-skeleton
FastAPI Skeleton App to serve machine learning models production-ready.
satellite-image-deep-learning/model-training-and-deployment
Training and deployment of deep learning models for satellite & aerial imagery
MarwanDebbiche/post-tuto-deployment
Build and deploy a machine learning app from scratch 🚀
BolajiAyodeji/deploy-ml-web-workshop
In this workshop, you will learn how to build a machine learning model using...
codingforentrepreneurs/AI-as-an-API
Learn to create & deploy a deep learning algorithm into a production REST API microservice using...