Skip to content

Easily deploy your machine models to production

Notifications You must be signed in to change notification settings

servomac/mldeploy

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

mldeploy: Easily deploy your machine models to production

mldeploy is a web application to convert your machine learning models into restful web APIs. Upload your scikit-learn, Keras or Tensorflow trained model and specify the features of your dataset. A prediction endpoint is provided to the user, exposing its machine learning model, ready to accept instances to predict.

⚠️ Security warning: This project unpickles untrusted objects, so arbitrary python code could be executed. Do not allow untrusted users to upload models to your deployment.

Usage

Configuration

TODO

How to Deploy

docker-compose up -d

Features

  • Expose a prediction JSON API from a trained persisted model
  • Support for multiple ML libraries: scikit-learn, keras, tensorflow
  • Statistics about prediction requests and responses

About

Easily deploy your machine models to production

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published