# melodyguan/enas

TensorFlow Code for paper "Efficient Neural Architecture Search via Parameter Sharing"

Repository: https://github.com/melodyguan/enas
Canonical: https://ross.abutalabs.com/products/enas
Homepage: https://arxiv.org/abs/1802.03268
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2019-06-18T14:02:10+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": 3113, "days_push": 2633, "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 1578, forks 383 (observed 2026-08-28T04:05:06.685290+00:00)

## What it is
Authors' TensorFlow implementation of Efficient Neural Architecture Search (ENAS), which discovers neural network architectures via parameter sharing and policy-gradient training of a controller. It includes experiments for CIFAR-10 image classification (macro and micro search spaces) and Penn Treebank language modeling, though the PTB implementation is known to be incorrect.

## Use cases
- search for neural network architectures automatically
- run ENAS experiments on CIFAR-10
- reproduce the ENAS paper results
- study neural architecture search with parameter sharing
- learn how NAS controllers are trained with policy gradient

## When to choose
- you want to reproduce or study the ENAS paper's CIFAR-10 experiments
- you need a reference implementation of parameter-sharing NAS
- you are researching neural architecture search methods

## When to avoid
- you need the Penn Treebank language modeling implementation (it is erroneous; use the corrected google-research version)
- you need a maintained, production-ready NAS framework
- you use PyTorch or modern TensorFlow versions

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: machine-learning, deep-learning, computer-vision
- platform: python
- tags: neural-architecture-search, tensorflow, enas, research-code, reinforcement-learning, natural-language-processing, gpu

## Member repositories
- melodyguan/enas (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:06.685290+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 2026-08-30T03:56:55.883665+00:00, confidence not recorded.
  - readme: https://github.com/melodyguan/enas (fetched 2026-08-28T04:05:06.685290+00:00, sha 533ad4b0a417)
  - homepage: https://arxiv.org/abs/1802.03268 (fetched 2026-08-29T11:27:20.794754+00:00, sha 468e13c5ee33)
  - site_page: https://info.arxiv.org/about/donate.html (fetched 2026-08-29T11:27:20.804286+00:00, sha cca9c3a11c56)
  - site_page: https://info.arxiv.org/about/ourmembers.html (fetched 2026-08-29T11:27:20.807841+00:00, sha 47cbc55ff1de)
  - site_page: https://info.arxiv.org/about (fetched 2026-08-29T11:27:20.809829+00:00, sha a1f16f915a9a)
  - site_page: https://info.arxiv.org/labs/index.html (fetched 2026-08-29T11:27:20.806153+00:00, sha b14a8d05a0ec)
- Data as of 2026-08-30T08:39:29.467469+00:00.