# jakesnell/prototypical-networks

Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"

Repository: https://github.com/jakesnell/prototypical-networks
Canonical: https://ross.abutalabs.com/products/prototypical-networks
Language: Python
License: MIT
License Family: permissive
Topics: few-shot, deep-learning, metric-learning, nips-2017, omniglot, pytorch
Last push: 2021-01-28T09:22:04+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3223, "days_push": 2043, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1235, forks 268 (observed 2026-08-28T04:04:04.989884+00:00)

## What it is
Reference PyTorch implementation of Prototypical Networks for few-shot classification from the NeurIPS 2017 paper. It includes training and evaluation scripts for the Omniglot dataset.

## Use cases
- reproduce prototypical networks results from the NeurIPS 2017 paper
- train a few-shot image classification model on Omniglot
- learn how metric-based few-shot learning works in PyTorch
- benchmark few-shot learning algorithms
- adapt prototypical networks to a custom few-shot dataset

## When to choose
- you need the official reference implementation of Prototypical Networks
- you want a simple, well-cited baseline for few-shot learning research
- you are working with Omniglot-style few-shot classification tasks

## When to avoid
- you need a maintained library with recent PyTorch support - the code targets PyTorch 0.4 and Python 3.6
- you want production-ready few-shot learning tooling rather than research code
- you need few-shot learning for NLP or other modalities out of the box

## Facets
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning, nlp
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: few-shot-learning, metric-learning, pytorch, research-code, omniglot, prototypical-networks, linux, gpu

## Member repositories
- jakesnell/prototypical-networks (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:04.989884+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:22:06.194164+00:00, confidence not recorded.
  - readme: https://github.com/jakesnell/prototypical-networks (fetched 2026-08-28T04:04:04.989884+00:00, sha 6350e5bbbcb5)
- Data as of 2026-08-30T08:39:29.467469+00:00.