2martens/masterthesis
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Removed left-over reference to early stopping

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2019-04-04 17:26:56 +02:00
parent 9a1f91892a
commit 17537b944b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/twomartens/masterthesis/aae/train.py
View File

@ -55,7 +55,7 @@ def train_simple(dataset: tf.data.Dataset,
""" """
Trains auto-encoder for given data set. Trains auto-encoder for given data set.
This function provides early stopping and creates checkpoints after every This function creates checkpoints after every
epoch as well as after finishing training (or stopping early). When starting epoch as well as after finishing training (or stopping early). When starting
this function with the same ``iteration`` then the training will try to this function with the same ``iteration`` then the training will try to
continue where it ended last time by restoring a saved checkpoint. continue where it ended last time by restoring a saved checkpoint.