Accommodates 2 changes in TF Datasets and Keras #176
Conversation
This file contains hidden or 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
… self.add_weight, so that calls to train can update the weights, and 2) steps per epoch is an integer as expected by "fit"
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Changes regarding TF Datasets
Automated downloads for CelebA dataset fail with unauthorized access errors. To circumvent this, I downloaded the data manually. Afterwards, I updated the notebook with parameters that let
download_and_preparepickup the manually downloaded files.Changes regarding Keras
Keras' model super class will not update weights if they are not added as layers or via self.add_weight,. I made the relevant updates, so that model.fit works again. Also, I made the value of per epoch into integer as expected by
fit.