Skip to content

Model Agnostic Meta Learning in TensorFlow 2.1

Notifications You must be signed in to change notification settings

gdao-research/maml

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Model Agnostic Meta Learning

Reproduce of MAML paper in toy example regression task (Sinusoid) using TensorFlow 2.1.

The loss curve comparison between a normal deep learning method and MAML:

An inference example of random new task trained with only 10 steps:

How to use:

  • Build Docker image from Dockerfile
  • Run python main.py to perform vanilla and MAML experiments

About

Model Agnostic Meta Learning in TensorFlow 2.1

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published