search

frankkramer-lab / MIScnn

A framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning
GNU General Public License v3.0
402 stars 116 forks source link

Fix the issue for cross_validation with ReduceLROnPlateau #71

Closed JimHeo closed 3 years ago

JimHeo commented 3 years ago

Hey,

Using k-fold cross validation with callback ReduceLROnPlateau, there is an issue. When the training of the first fold is over, learning rate is still reduced... Because of that, starting with the second fold, training becomes longer. So, I update the code of cross_validation function a little.

Cheers, Jim

muellerdo commented 3 years ago

Hey @JimHeo,

thanks for this great contribution! Accepted.

Cheers, Dominik