orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1078 stars · 217 forks observed · 2026-08-28

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

A PyTorch implementation of Prototypical Networks for few-shot learning, including the prototypical loss and episode-based batch sampler. It reproduces the reference paper's methodology on the Omniglot dataset with Vinyals-style splits.

Use cases

• implement prototypical networks in pytorch
• few-shot image classification
• reproduce results from the prototypical networks paper
• learn meta-learning and episode-based training
• train on the omniglot dataset with vinyals splits

When to choose

• you want a simple, readable PyTorch implementation of Prototypical Networks
• you need a prototypical loss or episodic batch sampler to reuse in your own few-shot project
• you want to reproduce paper results on Omniglot

When to avoid

• you need production-ready, actively maintained few-shot learning frameworks
• you want support for many datasets or modern meta-learning methods out of the box
• you need non-PyTorch (e.g., TensorFlow) implementations

Facets

library · maturity maintenance

machine-learning deep-learning machine-learning deep-learning computer-vision python few-shot-learning pytorch prototypical-networks meta-learning omniglot cnn

Member repositories

For agents

markdown · JSON · MCP: product_card(name="orobix/Prototypical-Networks-for-Few-shot-Learning-PyTorch")