Subfunctions now also work with activation output

frankkramer-lab / MIScnn

A framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning

GNU General Public License v3.0

400 stars 116 forks source link

Subfunctions now also work with activation output #118

Closed Dennis182 closed 2 years ago

Deathlymad commented 2 years ago

handled merge conflicts. Didn't really look at the code itself but it seemed alright.

Deathlymad commented 2 years ago

The dimensionality asserts failed. In particular at resampling. Maybe some other assumptions are also made there. You should probably give those another look and while you're at it it would be great if you'd add an activation_output test case.

Dennis182 commented 2 years ago

Ich habe in den Subfunktionen wohl in letzter Zeit noch Änderungen gemacht, damit reduzieren sich die Fehler auf den Mismatch bei test_SUBFUNCTIONS_RESAMPLING_postprocessing_activationOutput

muellerdo commented 2 years ago

@all, please use English as communication language.

@Dennis182, isn't this issue already fixed in the dev branch with 1d15ca1ecda73207c4de3837ea785cddf84d4712 and a37fb858f6c667566d214dfdf7ea0faf6dc77d57?

Dennis182 commented 2 years ago

You're right, I guess I missed that.

muellerdo commented 2 years ago

No problem :D