Skip to content
This repository has been archived by the owner on Mar 17, 2021. It is now read-only.

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

Merged
merged 1 commit into from
Jan 17, 2020
Merged

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

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions niftynet/application/gan_application.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -215,10 +215,10 @@ def switch_sampler(for_training):
collection=CONSOLE)
# variables to display in tensorboard
outputs_collector.add_to_collection(
var=lossG, name='lossG', average_over_devices=False,
var=lossD, name='lossD', average_over_devices=True,
collection=TF_SUMMARIES)
outputs_collector.add_to_collection(
var=lossG, name='lossD', average_over_devices=True,
var=lossG, name='lossG', average_over_devices=False,
collection=TF_SUMMARIES)

with tf.name_scope('Optimiser'):
Expand Down