gabrielhuang/reptile-pytorch

A PyTorch implementation of OpenAI's REPTILE algorithm

45
/ 100
Emerging

This project helps machine learning researchers and practitioners experiment with meta-learning algorithms on the Omniglot dataset. It takes raw Omniglot images and configuration parameters for few-shot learning tasks as input. The output is a trained model capable of quickly adapting to new, unseen character recognition tasks, along with TensorboardX logs for monitoring training progress. This is for those researching or applying few-shot learning for image classification.

220 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher or student looking to implement and experiment with the Reptile meta-learning algorithm on the Omniglot dataset for few-shot image classification.

Not ideal if you need a production-ready solution, require support for datasets beyond Omniglot, or are not comfortable working with Python code directly.

meta-learning few-shot learning image classification machine learning research model training
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

220

Forks

37

Language

Jupyter Notebook

License

BSD-2-Clause

Last pushed

Dec 31, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/gabrielhuang/reptile-pytorch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.