tristandeleu/pytorch-meta
A PyTorch library providing datasets, benchmarks, and utilities for few-shot meta-learning research.
Not currently ranked — collecting fresh signals.
star history
Torchmeta is a collection of extensions and data-loaders for few-shot learning and meta-learning in PyTorch. It includes popular meta-learning benchmarks like Omniglot, Mini-ImageNet, and Tiered-ImageNet, with a unified interface for both few-shot classification and regression problems. The library provides a MetaModule base class that simplifies creating gradient-based meta-learning models, fully compatible with standard PyTorch DataLoader and torchvision.
Frequently asked
- What is tristandeleu/pytorch-meta?
- A PyTorch library providing datasets, benchmarks, and utilities for few-shot meta-learning research.
- Is pytorch-meta open source?
- Yes — tristandeleu/pytorch-meta is open source, released under the MIT license.
- What language is pytorch-meta written in?
- tristandeleu/pytorch-meta is primarily written in Python.
- How popular is pytorch-meta?
- tristandeleu/pytorch-meta has 2.1k stars on GitHub.
- Where can I find pytorch-meta?
- tristandeleu/pytorch-meta is on GitHub at https://github.com/tristandeleu/pytorch-meta.