# quark0/darts

Differentiable architecture search for convolutional and recurrent networks

Repository: https://github.com/quark0/darts
Canonical: https://ross.abutalabs.com/products/quark0-darts
Homepage: https://arxiv.org/abs/1806.09055
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, automl, image-classification, language-modeling, pytorch, convolutional-networks, recurrent-networks, neural-architecture-search
Last push: 2021-01-03T02:21:40+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2991, "days_push": 2069, "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 3997, forks 836 (observed 2026-08-28T04:08:31.948434+00:00)

## What it is
DARTS is the official PyTorch implementation of the ICLR 2019 paper 'DARTS: Differentiable Architecture Search', which performs neural architecture search via continuous relaxation and gradient descent. It searches convolutional cells for image classification (CIFAR-10, ImageNet) and recurrent cells for language modeling (PTB, WikiText-2), requiring only a single GPU, and ships pretrained models.

## Use cases
- search for a convolutional network architecture for image classification
- search for a recurrent cell for language modeling
- run differentiable NAS on a single GPU
- evaluate pretrained DARTS CNN and RNN models
- reproduce the DARTS paper experiments
- learn how gradient-based architecture search works

## When to choose
- you want to reproduce or build on the DARTS paper
- you need a fast, single-GPU differentiable NAS baseline
- you want pretrained DARTS cells for CIFAR-10, ImageNet, or PTB

## When to avoid
- you need a maintained production AutoML tool (pinned to PyTorch 0.3.1)
- you want a general-purpose NAS framework with pluggable search spaces
- you need support for modern PyTorch versions or recent hardware

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: deep-learning, machine-learning, computer-vision
- platform: python
- tags: neural-architecture-search, automl, darts, differentiable-search, pytorch, research-code, image-classification, language-modeling, natural-language-processing, gpu

## Member repositories
- quark0/darts (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:31.948434+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 2026-08-29T18:24:10.491853+00:00, confidence not recorded.
  - readme: https://github.com/quark0/darts (fetched 2026-08-28T04:08:31.948434+00:00, sha 3cc6748c9498)
  - homepage: https://arxiv.org/abs/1806.09055 (fetched 2026-08-29T09:17:20.164792+00:00, sha 3928b48f9652)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T09:17:20.179596+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T09:17:20.183293+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T09:17:20.185208+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T09:17:20.181626+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.