-
Notifications
You must be signed in to change notification settings - Fork 130
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
47 additions
and
10 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
0243a03
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This commit seems to break the training process - during the initial sampling phase, there is a mismatch in the input dimensions.
For instance, if I run the following training command (where the test has a batch size of 5):
THEANO_FLAGS=mode=FAST_RUN,device=cuda,floatX=float32,dnn.enabled=True python2 train.py --prototype prototype_test > Model_Output.txt
I then get the following error:
ValueError: Input dimension mis-match. (input[0].shape[0] = 1, input[1].shape[0] = 5)
This error did not occur in the previous versions.
0243a03
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks for spotting this! I've made a new commit which should fix the bug.