sicara/easy-few-shot-learning

Health v2 · maintenance only

Adoption not part of the score

1313 stars · 170 forks observed · 2026-08-28

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

A Python library (easyfsl) with ready-to-use code and tutorial notebooks for few-shot image classification and meta-learning, built on PyTorch. It pairs each implementation with explanatory notebooks so learners can follow along step by step.

Use cases

• learn few-shot learning from scratch with tutorials
• train a few-shot image classifier in pytorch
• run episodic training for prototypical networks
• evaluate few-shot models on benchmark datasets
• apply meta-learning to a small image dataset
• get clear reference code for few-shot classification research

When to choose

• you are new to few-shot learning and want guided notebooks
• you need simple, well-documented few-shot classification code for a project
• you want a lightweight PyTorch library rather than a huge research codebase

When to avoid

• you need many state-of-the-art few-shot methods in one framework
• you need production-scale training pipelines or distributed training
• your task is not image classification

Facets

library · maturity stable

machine-learning deep-learning machine-learning deep-learning computer-vision tutorials python few-shot-learning meta-learning pytorch image-classification tutorial-notebooks

Member repositories

For agents

markdown · JSON · MCP: product_card(name="sicara/easy-few-shot-learning")