Skip to content

Releases: Xylambda/torchfitter

Remove Manager. Update examples

18 May 17:57
be51a1c

Choose a tag to compare

WIP, ENH, BLD: fix gh-pages deployment. Add more examples (#50)

* WIP, ENH, BLD: fix gh-pages deployment. Add more examples

* CLN: remove manager. Update requirements

* CLN: remove experiments folder

* DOC, CLN: remove Manager. Update docs

v4.2.2

18 Apr 14:06
870100d

Choose a tag to compare

BUG: fix accelerator initialization

v4.2.1

10 Sep 15:40
4673b31

Choose a tag to compare

Changed

  • Callbacks have been reorganized in folders.
  • Update requirements.
  • Update gh-pages.yml.
  • Update README.md
  • Update mixed_precision parameter and usage.

Fixed

  • Progress bar will only be created under the main process.
  • Logging now is handled by accelerate library.

v4.2.0: ENH: regularization as callbacks (#42)

08 Aug 19:04
4673b31

Choose a tag to compare

Added

  • Add torch.ditribution example, with code taken from Romain Strock.
  • Add predict method to Trainer. #38
  • Add functions to freeze and unfreeze model. #43
  • Add function to transform dataset into time series dataset.

Fixed

  • Metrics are now moved to the execution device #41.
  • Log level is now used in the Trainer. #40
  • LearningRateScheduler now does not crash in first epoch when on_train is False. #36

Changed

  • Make regularization part of the callbacks system. #37
  • Divide utils into three submodules: convenience,preprocessing and data.
  • Update requirements to avoid conflicts.
  • Update some tests.

Removed

  • Remove old regularization module and all related code.

v4.1.2

24 Dec 19:01

Choose a tag to compare

BLD: fix PyPi deployment file