# facebookresearch/mixup-cifar10

mixup: Beyond Empirical Risk Minimization

Repository: https://github.com/facebookresearch/mixup-cifar10
Canonical: https://ross.abutalabs.com/products/mixup-cifar10
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2021-10-12T21:33:03+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3117, "days_push": 1786, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1197, forks 230 (observed 2026-08-28T04:03:57.401861+00:00)

## What it is
Official PyTorch implementation of mixup, a data augmentation technique that trains neural networks on convex combinations of image pairs and their labels. This repository reproduces the CIFAR-10 results from the ICLR 2018 paper 'mixup: Beyond Empirical Risk Minimization'.

## Use cases
- implement mixup data augmentation in pytorch
- reproduce mixup paper results on cifar10
- improve neural network regularization with data augmentation
- train image classifiers with mixup
- learn how mixup works from reference code

## When to choose
- you want the reference implementation of mixup from the original authors
- you are reproducing the paper's CIFAR-10 experiments
- you need a simple example of mixup in PyTorch

## When to avoid
- you need a maintained, production-ready augmentation library
- you need a permissive license (this is CC-BY-NC)
- you work on Windows or need modern Python versions
- you want mixup support for frameworks other than PyTorch

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, data-generation
- domain: machine-learning, deep-learning, computer-vision
- platform: python
- tags: data-augmentation, pytorch, cifar10, research-code, regularization, linux, macos, gpu

## Member repositories
- facebookresearch/mixup-cifar10 (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:57.401861+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 2026-08-30T06:21:26.951145+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/mixup-cifar10 (fetched 2026-08-28T04:03:57.401861+00:00, sha f7a4b7bed7df)
- Data as of 2026-08-30T08:39:29.467469+00:00.