tuvovan/ml_in_production
A set of demo of deploying a Machine Learning Model in production using various methods
This project helps machine learning engineers or MLOps practitioners take a trained machine learning model, like a TensorFlow image classifier, and make it available for others to use, often via web requests. It demonstrates various methods for packaging and deploying these models so they can process new data and return predictions. The ideal user is someone responsible for moving models from development to a live, operational environment.
No commits in the last 6 months.
Use this if you need to understand different strategies for putting a machine learning model into a production environment where it can be continuously queried.
Not ideal if you are looking for guidance on how to train machine learning models or optimize their performance, rather than deploying them.
Stars
61
Forks
22
Language
Python
License
—
Category
Last pushed
Sep 22, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mlops/tuvovan/ml_in_production"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
combust/mleap
MLeap: Deploy ML Pipelines to Production
ml-tooling/opyrator
🪄 Turns your machine learning code into microservices with web API, interactive GUI, and more.
jpmorganchase/inference-server
Deploy your AI/ML model to Amazon SageMaker for Real-Time Inference and Batch Transform using...
ebhy/budgetml
Deploy a ML inference service on a budget in less than 10 lines of code.
SocAIty/APIPod
Create web-APIs for long-running tasks. Job based task handling. Get the result with the job id...