floodsung/LearningToCompare_FSL

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1076 stars · 263 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Official PyTorch implementation of the Relation Network for Few-Shot Learning from the CVPR 2018 paper 'Learning to Compare'. It includes training and testing scripts for Omniglot and mini-ImageNet few-shot classification benchmarks.

Use cases

• reproduce relation network few-shot learning results
• train few-shot image classification on omniglot
• run 5-way 1-shot experiments on mini-ImageNet
• learn meta-learning with a learnable similarity metric
• baseline for few-shot learning research
• understand relation network architecture in pytorch

When to choose

• you need a reference implementation of the CVPR 2018 Relation Network paper
• you want to benchmark few-shot learning on Omniglot or mini-ImageNet
• you are studying metric-based meta-learning approaches

When to avoid

• you need a maintained library with modern PyTorch support (code targets Python 2.7 and PyTorch 0.3)
• you want production-ready few-shot learning tooling
• you need few-shot learning beyond image classification

Facets

library · maturity maintenance

machine-learning deep-learning machine-learning deep-learning computer-vision python few-shot-learning meta-learning relation-network pytorch research-code cvpr-2018 omniglot mini-imagenet gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="floodsung/LearningToCompare_FSL")