Daniel CARRON authored 11 months ago and André Anjos committed 8 months ago

Some failing pre-commit checks have been ignored for now

Daniel CARRON authored 11 months ago and André Anjos committed 8 months ago

Since the core module and mednet-specific code have been split in
separate modules,getLogger(__name__) was returning different results.
The logger names have been hardcoded for now to fix issues during
testing but a better solution needs to be found.

3d cnn visceral

See merge request biosignal/software/mednet!51

Fix montgomery-shenzhen-indian-tbx11k datamodule

See merge request biosignal/software/mednet!55

[doc] fix documentation job by using numpy 1.26 instead of stable in sphinx

See merge request biosignal/software/mednet!53

Remove elastic deformation parallelisation

See merge request biosignal/software/mednet!50

Optimise device allocation for all attributes used in the training loop

Closes #78

See merge request biosignal/software/mednet!49

[models.model] Explicitly set the datamodule batch-size to 1 to avoid issues when running in an combo-experiment

[models.model] Implement to() method to move all computing to the designated accelerator device, including losses and augmentations