Fix bug: tf.add_n([loss] + reg_losses) rather than loss + reg_losses

Browse Source

...

This commit is contained in:

Aurelien Geron

2017-03-04 12:36:25 +01:00

parent 002fd669c5

commit a9c1c20a9b

2 changed files with 345 additions and 340 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

474

15_autoencoders.ipynb

File diff suppressed because one or more lines are too long