Torchmeta: A Meta-Learning library for PyTorch

TL;DR

Torchmeta is a PyTorch library that simplifies the development and evaluation of meta-learning algorithms across multiple standardized benchmarks, promoting fair comparison and easier dataset handling.

Contribution

It introduces a unified data-loading framework and extensions for PyTorch to facilitate meta-learning research on various datasets.

Findings

Provides data-loaders for standard meta-learning benchmarks

Enables seamless evaluation across multiple datasets

Simplifies model development for meta-learning algorithms

Abstract

The constant introduction of standardized benchmarks in the literature has helped accelerating the recent advances in meta-learning research. They offer a way to get a fair comparison between different algorithms, and the wide range of datasets available allows full control over the complexity of this evaluation. However, for a large majority of code available online, the data pipeline is often specific to one dataset, and testing on another dataset requires significant rework. We introduce Torchmeta, a library built on top of PyTorch that enables seamless and consistent evaluation of meta-learning algorithms on multiple datasets, by providing data-loaders for most of the standard benchmarks in few-shot classification and regression, with a new meta-dataset abstraction. It also features some extensions for PyTorch to simplify the development of models compatible with meta-learning algorithms. The code is available here: https://github.com/tristandeleu/pytorch-meta