Torchmeta: A Meta-Learning library for PyTorch

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

References in corpus (4)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Meta-Learning with Latent Embedding Optimization
• Fast Context Adaptation via Meta-Learning
• Uncertainty in Multitask Transfer Learning

Cited by in corpus (11)

• Torchreid: A Library for Deep Learning Person Re-Identification in Pytorch
• learn2learn: A Library for Meta-Learning Research
• Meta-Learning Symmetries by Reparameterization
• A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings
• On Episodes, Prototypical Networks, and Few-shot Learning
• p-Meta: Towards On-device Deep Model Adaptation
• The TCGA Meta-Dataset Clinical Benchmark
• Meta Learning for Few-Shot One-class Classification
• FLEX: Unifying Evaluation for Few-Shot NLP
• Uniform Priors for Data-Efficient Transfer
• Minimax Optimization with Smooth Algorithmic Adversaries