Fixed bug in KL_loss calculation for VAE validation step during training #2000
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
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
|
Yes! Thank you for the PR. Please go ahead and make the DCO pass and I will approve it |
…[email protected]> I, Muhammad Nabi Yasinzai <[email protected]>, hereby add my Signed-off-by to this commit: bca2c13 Signed-off-by: Muhammad Nabi Yasinzai <[email protected]>
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Outdated suggestions cannot be applied.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.
Fixes # .
Description
The KL_loss is included in the Validation loss calculation during VAE-training validation step. However, the correct z_mu, z_sigma are not passed. Either this val_epoch_losses["kl_loss"] should always be zero if that was the intension or the correct z_mu, z_sigma should be passed.
Checks