gabrielhuang/reptile-pytorch
A PyTorch implementation of OpenAI's REPTILE algorithm
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.
Stars
220
Forks
37
Language
Jupyter Notebook
License
BSD-2-Clause
Category
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.
Higher-rated alternatives
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild