dragen1860/MAML-Pytorch
PyTorch implementation of Model-Agnostic Meta-Learning (MAML) for few-shot image classification on MiniImagenet and Omniglot datasets.
Not currently ranked — collecting fresh signals.
star history
This repository provides a clean implementation of the MAML meta-learning algorithm in PyTorch. MAML learns model parameters such that few gradient steps on a new task produce good generalization. The implementation supports supervised learning experiments on MiniImagenet (few-shot classification) and Omniglot datasets, including both the full MAML algorithm and First-Order approximation (Reptile) variants.
Frequently asked
- What is dragen1860/MAML-Pytorch?
- PyTorch implementation of Model-Agnostic Meta-Learning (MAML) for few-shot image classification on MiniImagenet and Omniglot datasets.
- Is MAML-Pytorch open source?
- Yes — dragen1860/MAML-Pytorch is open source, released under the MIT license.
- What language is MAML-Pytorch written in?
- dragen1860/MAML-Pytorch is primarily written in Python.
- How popular is MAML-Pytorch?
- dragen1860/MAML-Pytorch has 2.5k stars on GitHub.
- Where can I find MAML-Pytorch?
- dragen1860/MAML-Pytorch is on GitHub at https://github.com/dragen1860/MAML-Pytorch.