Better cifar10.py #33
Open
Conversation
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
…le batch sizes, and supports TensorBoard
raghakot
reviewed
Feb 8, 2017
raghakot
reviewed
Feb 8, 2017
cifar10.py
Outdated
| model_checkpoint = ModelCheckpoint(out_dir+'weights.hdf5', monitor='val_loss', verbose=0, save_best_only=True, save_weights_only=False, mode='auto') | ||
| callbacks=[lr_reducer, early_stopper, csv] | ||
|
|
||
| if K.image_dim_ordering() == 'tf': |
There was a problem hiding this comment.
image dim ordering doesn't imply tensorflow backend. Is there a way to check 'backend' instead?
There was a problem hiding this comment.
You're right, but I don't know the correct way... https://keras.io/backend/
There was a problem hiding this comment.
Use K.backend() method. It is at the end of the doc you linked.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
cifar10.py provides more debug output, performance charts, configurable batch sizes, supports TensorBoard, and provides better information about how the run is going, and to put checkpoints in folders based on time so they aren't overwritten inadvertently.