# D-X-Y/AutoDL-Projects

Automated deep learning algorithms implemented in PyTorch.

Repository: https://github.com/D-X-Y/AutoDL-Projects
Canonical: https://ross.abutalabs.com/products/autodl-projects
Language: Python
License: MIT
License Family: permissive
Topics: nas, neural-architecture-search, automl, pytorch, autodl
Last push: 2022-04-24T22:18:16+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": 2771, "days_push": 1592, "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 1581, forks 288 (observed 2026-08-28T04:05:07.096141+00:00)

## What it is
AutoDL-Projects is a PyTorch library implementing automated deep learning algorithms, including neural architecture search (NAS) methods like DARTS, GDAS, SETN, and TAS, plus hyper-parameter optimization. It unifies multiple AutoDL algorithms in a single lightweight codebase for beginners, engineers, and researchers.

## Use cases
- run neural architecture search experiments in pytorch
- try different automl algorithms in one codebase
- implement and benchmark new NAS algorithms for research
- evaluate whether automated deep learning helps my project
- reproduce DARTS or GDAS search results
- learn hyper-parameter optimization and NAS as a beginner

## When to choose
- you want multiple NAS/HPO algorithms in one consistent codebase
- you are a researcher prototyping new AutoDL methods
- you want simple dependencies and readable reference implementations of published papers

## When to avoid
- you need a production AutoML platform with GUI and pipelines
- you work outside PyTorch (e.g., TensorFlow or JAX)
- you need actively maintained support for the latest models and APIs

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: nas, neural-architecture-search, automl, hyperparameter-optimization, pytorch, research, gpu

## Member repositories
- D-X-Y/AutoDL-Projects (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:07.096141+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 2026-08-30T03:56:20.877302+00:00, confidence not recorded.
  - readme: https://github.com/D-X-Y/AutoDL-Projects (fetched 2026-08-28T04:05:07.096141+00:00, sha c28e6c90c902)
- Data as of 2026-08-30T08:39:29.467469+00:00.