Fixed bug when logging discriminator loss for tensorboard in GAN application - Githubissues

NifTK / NiftyNet

[unmaintained] An open-source convolutional neural networks platform for research in medical image analysis and image-guided therapy

http://niftynet.io

Apache License 2.0

1.36k stars 404 forks source link

Fixed bug when logging discriminator loss for tensorboard in GAN application #475

Closed javierbg closed 4 years ago

javierbg commented 4 years ago

Status

READY

Description

There was a bug when logging the Discrimiantor loss in the GAN application: the Generator loss would be logged instead. This fixes that.

Types of changes

[x] Bug fix (non-breaking change which fixes an issue)
[ ] New feature (non-breaking change which adds functionality)
[ ] Breaking change (fix or feature that would cause existing functionality to change)
[x] My code follows the code style of this project.
[ ] I have added tests to cover my changes.
[ ] All new and existing tests passed.

Todos

[ ] Tests
[ ] Documentation

I ran the tests before and after the change, and the same error came up:

.2020-01-16 13:44:12.961729: F ./tensorflow/core/util/mkl_util.h:636] Check failed: dims == sizes.size() (5 vs. 4)

I'm very confident that this minor change doesn't break anything and I was able to check that it works in my own code.

Impacted Areas in Application

List general components of the application that this PR will affect:

niftynet.application.GANApplication