Skip to main content

A surrogate benchmark for neural architecture search

Project description

NAS-Bench-301

This repository containts code for the paper: "NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search".

The surrogate models can be downloaded on figshare. This includes the models for v0.9 and v1.0 as well as the dataset that was used to train the surrogate models. We also provide the full training logs for all architectures, which include learning curves on the train, validation and test sets. These can be automatically downloaded, please see nasbench301/example.py.

To install all requirements (this may take a few minutes), run

$ cat requirements.txt | xargs -n 1 -L 1 pip install
$ pip install nasbench301

If installing directly from github

$ git clone https://github.com/automl/nasbench301
$ cd nasbench301
$ cat requirements.txt | xargs -n 1 -L 1 pip install
$ pip install .

To run the example

$ python3 nasbench301/example.py

To fit a surrogate model run

$ python3 fit_model.py --model gnn_gin --nasbench_data PATH_TO_NB_301_DATA_ROOT --data_config_path configs/data_configs/nb_301.json  --log_dir LOG_DIR

NOTE: This codebase is still subject to changes. Upcoming updates include improved versions of the surrogate models and code for all experiments from the paper. The API may still be subject to changes.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

nasbench301-0.3.tar.gz (1.8 MB view details)

Uploaded Source

Built Distribution

nasbench301-0.3-py3-none-any.whl (2.1 MB view details)

Uploaded Python 3

File details

Details for the file nasbench301-0.3.tar.gz.

File metadata

  • Download URL: nasbench301-0.3.tar.gz
  • Upload date:
  • Size: 1.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.23.0 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.7.7

File hashes

Hashes for nasbench301-0.3.tar.gz
Algorithm Hash digest
SHA256 51aaf7024a7d41bb6feb4f3d35e74e49bcaac721a6dd53e7c7bdef159ae16707
MD5 6492ea1a436569be1b2621266b385f73
BLAKE2b-256 2f49b0779342ff1e108db4164d04626aed237241ed9e7314514d412ed1c0f8ed

See more details on using hashes here.

File details

Details for the file nasbench301-0.3-py3-none-any.whl.

File metadata

  • Download URL: nasbench301-0.3-py3-none-any.whl
  • Upload date:
  • Size: 2.1 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.23.0 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.7.7

File hashes

Hashes for nasbench301-0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 ad53672d072abdc2b5c4c14604af53a61cf6927123a9962f35d7b067900b962d
MD5 f1bfc36d347c7cf4af38402d7a29fdc3
BLAKE2b-256 8b4194e4d390cb450c4f4eca091e0d2f09948e36f9baa0cf58f778b8626ff262

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page