Skip to main content

Framework for training generic ml models

Project description

Yes, there is no documentation at the moment, its not really intended as usable to the outside world atm, I personally need a convenient pip install.

Konductor

PyPI - Package Version PyPI - Python Version PyPI - License CircleCI Codecov codestyle

Model training framework bundled with performance evaluation and comparison tools for rapid prototyping. Go deep into setting up automatic configuration for ablations or quickly throw in a dataloader, model and loss function and run distributed training in seconds.

The aims of this project are
  • Empower you to only need to touch a few parts of the framework to get some wacky non-standard training loop done.

  • Easily roll in existing code bases into this framework so you can git clone yolo-69, register it to konductor, throw in your data and start training instead of whatever random framework of their codebase.

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

konductor-0.0.8.tar.gz (80.5 kB view details)

Uploaded Source

Built Distribution

konductor-0.0.8-py3-none-any.whl (92.4 kB view details)

Uploaded Python 3

File details

Details for the file konductor-0.0.8.tar.gz.

File metadata

  • Download URL: konductor-0.0.8.tar.gz
  • Upload date:
  • Size: 80.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.12.5

File hashes

Hashes for konductor-0.0.8.tar.gz
Algorithm Hash digest
SHA256 5e2dcfcf8c65549f5502b479da7147bff9bd6abb2cdbdbd6a5c3ba2b179ecea2
MD5 47185524d4a6664cf3535965de1c3493
BLAKE2b-256 3fd2426bd76fb74add1772666875ad72449c75574131d937184bce33e171b843

See more details on using hashes here.

File details

Details for the file konductor-0.0.8-py3-none-any.whl.

File metadata

  • Download URL: konductor-0.0.8-py3-none-any.whl
  • Upload date:
  • Size: 92.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.0 CPython/3.12.5

File hashes

Hashes for konductor-0.0.8-py3-none-any.whl
Algorithm Hash digest
SHA256 258477a991b5e1bcc6fcf1c03628f73098c9c3ebf89c3d99b0fb0f0a42c2949d
MD5 f1821c1bd5fe3e4b416ec492a5124b57
BLAKE2b-256 a4a338262f6915cfbb65d4111bcddb92ff1f0019da96e42a80618581ab10fb13

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