Skip to main content

initial working version for a random walk and model <> string conversions

Project description

uninas

This repository provides a framework to create instances of UNINas search space and walk through the space.

Testing

Initial string format

The string is structured by stages, separated by //. Each stage contains a sequence of blocks, separated by /. We support the following number of stages and blocks: (2, 3, 5, 2), e.g. MODEL_STRING='E/R//T/T/T//T/T/T/T/T//T/T'

In this example, the respective characters denote blocks corresponding to:

  • T Transformer
  • E EfficientNet
  • R ResNet

Instead of these variants (T, E, R), any plausible structure of the following form can be used:

subblock1[XXX]subblock1subblock2[YYY],

where XXX and YYY is a recursive graph representation obtained via each Node's method .to_string(). An example corresponding to MODEL_STRING='E/R//T/T/T//T/T/T/T/T//T/T' can be found in model_string.txt

python test.py --init-model <MODEL_STRING>

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

uninas-1.0.0.tar.gz (15.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

uninas-1.0.0-py3-none-any.whl (21.1 kB view details)

Uploaded Python 3

File details

Details for the file uninas-1.0.0.tar.gz.

File metadata

  • Download URL: uninas-1.0.0.tar.gz
  • Upload date:
  • Size: 15.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for uninas-1.0.0.tar.gz
Algorithm Hash digest
SHA256 51f02f78fdea3d38c05aa990f48aefd8a6a3fe96177a12720a9fda7b554e5037
MD5 1f5227c7bfb67daa46baa1c17cf3e200
BLAKE2b-256 d7e6e57dc6d17a40d201f01098102aa1e89ad5f8a60d092a141b91acac1d146b

See more details on using hashes here.

File details

Details for the file uninas-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: uninas-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 21.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.9

File hashes

Hashes for uninas-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 25308aa3215ac0286769a8d2528680f014ad0d0e25880f371e3cf122efc02cbf
MD5 9826dd950742b4e2ece3abc548329381
BLAKE2b-256 d239332e51c6542517a3c5cf50bd1c62a8813d80f00842e0d3720e2de9164a92

See more details on using hashes here.

Supported by

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