Differentiable Architecture Search theorist for AutoRA

Project description

AutoRA Differentiable Architecture Search

autora-theorist-darts is a Python module for fitting data using differentiable architecture search, built on AutoRA.

Website: https://autoresearch.github.io/autora/

User Guide

You will need:

python 3.8 or greater: https://www.python.org/downloads/
graphviz (optional, required for computation graph visualizations): https://graphviz.org/download/

Install DARTS as part of the autora package:

pip install -U "autora[theorist-darts]"

It is recommended to use a python environment manager like virtualenv.

Check your installation by running:

python -c "from autora.theorist.darts import DARTSRegressor; DARTSRegressor()"

Project details

Release history Release notifications | RSS feed

This version

1.1.0

Jul 28, 2024

1.0.0

May 31, 2023

1.0.0a5 pre-release

May 2, 2023

1.0.0a4 pre-release

May 1, 2023

1.0.0a3 pre-release

Apr 27, 2023

1.0.0a2 pre-release

Apr 27, 2023

1.0.0a1 pre-release

Apr 27, 2023

1.0.0a0 pre-release

Apr 27, 2023

Download files

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

Source Distribution

autora_theorist_darts-1.1.0.tar.gz (532.6 kB view details)

Uploaded Jul 28, 2024 Source

Built Distribution

autora_theorist_darts-1.1.0-py3-none-any.whl (32.6 kB view details)

Uploaded Jul 28, 2024 Python 3

File details

Details for the file autora_theorist_darts-1.1.0.tar.gz.

File metadata

Download URL: autora_theorist_darts-1.1.0.tar.gz
Upload date: Jul 28, 2024
Size: 532.6 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/5.1.1 CPython/3.9.19

File hashes

Hashes for autora_theorist_darts-1.1.0.tar.gz
Algorithm	Hash digest
SHA256	`79b74f9b295cc6e0face31c999f17883f27d46e53cdc8fa4aeb363007914c7ad`
MD5	`afd78b52025484e12e93ea5063634036`
BLAKE2b-256	`fee559f47019aab5582a9b7104db8aca9a21d1e1f2f2428d39d8ec759299b26a`

See more details on using hashes here.

Provenance

File details

Details for the file autora_theorist_darts-1.1.0-py3-none-any.whl.

File metadata

Download URL: autora_theorist_darts-1.1.0-py3-none-any.whl
Upload date: Jul 28, 2024
Size: 32.6 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/5.1.1 CPython/3.9.19

File hashes

Hashes for autora_theorist_darts-1.1.0-py3-none-any.whl
Algorithm	Hash digest
SHA256	`7fb7fde7cdabc2ae7a5409a303a5766e6f3d73677c50c97586d232bd10090590`
MD5	`1227a07ff56e89501a9f4d560ddbb025`
BLAKE2b-256	`562d99a95a8576739b88eea4ca9e7981121ec08425a33b8b9e50dc6b6d316814`