# RL-VIG/LibFewShot

[TPAMI 2023] LibFewShot: A Comprehensive Library for Few-shot Learning.

Repository: https://github.com/RL-VIG/LibFewShot
Canonical: https://ross.abutalabs.com/products/libfewshot
Language: Python
License: MIT
License Family: permissive
Topics: few-shot-learning, meta-learning, fine-tuning, image-classification, pytorch
Last push: 2025-10-27T06:51:35+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 49, release rhythm 35, longevity 100
- inputs: {"age_days": 1855, "days_push": 310, "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 1069, forks 200 (observed 2026-08-28T04:03:27.753380+00:00)

## What it is
LibFewShot is a comprehensive PyTorch library for few-shot learning, implementing many fine-tuning, meta-learning, and metric-learning methods from top venues. It provides a unified framework for training, evaluating, and reproducing few-shot image classification research.

## Use cases
- reproduce few-shot learning paper results
- train a prototypical network baseline
- compare meta-learning methods like MAML and R2D2
- benchmark metric-learning few-shot classifiers
- develop a new few-shot learning method on a unified codebase
- fine-tune models for low-shot image classification

## When to choose
- you need a unified, well-documented framework for few-shot image classification research
- you want to reproduce or compare many published few-shot methods in one codebase
- you are building new few-shot algorithms on PyTorch

## When to avoid
- your task is not image classification (e.g., few-shot NLP or detection)
- you need production deployment rather than research experimentation
- you do not work in PyTorch

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning
- domain: machine-learning, computer-vision, image-processing, artificial-intelligence
- platform: python, cross-platform
- tags: few-shot-learning, meta-learning, metric-learning, fine-tuning, pytorch, image-classification, research-library, gpu

## Member repositories
- RL-VIG/LibFewShot (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:27.753380+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 2026-08-30T06:54:24.551142+00:00, confidence not recorded.
  - readme: https://github.com/RL-VIG/LibFewShot (fetched 2026-08-28T04:03:27.753380+00:00, sha c2742524ce7d)
- Data as of 2026-08-30T08:39:29.467469+00:00.