# oscarknagg/few-shot

Repository for few-shot learning machine learning projects

Repository: https://github.com/oscarknagg/few-shot
Canonical: https://ross.abutalabs.com/products/few-shot
Language: Python
License: MIT
License Family: permissive
Topics: machine-learning, pytorch, few-shot-learning, research, meta-learning, maml, omniglot, miniimagenet
Last push: 2019-11-25T04:18:31+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2864, "days_push": 2473, "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 1284, forks 244 (observed 2026-08-28T04:04:14.484614+00:00)

## What it is
A PyTorch repository with clean, tested implementations that reproduce few-shot learning and meta-learning research papers such as Prototypical Networks and MAML. It includes dataset preparation scripts for Omniglot and miniImageNet and experiment scripts matching published benchmark results.

## Use cases
- reproduce few-shot learning paper results in pytorch
- learn how prototypical networks work
- implement MAML meta-learning
- run experiments on omniglot and miniimagenet
- study clean implementations of meta-learning algorithms
- benchmark n-way k-shot classification models

## When to choose
- you want readable, tested reference implementations of few-shot learning papers
- you need reproducible Prototypical Networks or MAML baselines
- you are learning meta-learning concepts with working code

## When to avoid
- you need production-ready few-shot learning pipelines
- you want the latest few-shot learning methods or active maintenance
- you need a high-level framework rather than research code

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: few-shot-learning, meta-learning, pytorch, maml, prototypical-networks, omniglot, miniimagenet, research-reproduction, research, gpu, linux, macos

## Member repositories
- oscarknagg/few-shot (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:14.484614+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 2026-08-30T04:56:45.959843+00:00, confidence not recorded.
  - readme: https://github.com/oscarknagg/few-shot (fetched 2026-08-28T04:04:14.484614+00:00, sha 987fa587990d)
- Data as of 2026-08-30T08:39:29.467469+00:00.