Fix MLP/Recurrent-based memory inference complications #512
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
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
This was
linked to
issues
Apr 7, 2023
kdgutier
changed the title
cchallu
approved these changes
Apr 11, 2023
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Outdated suggestions cannot be applied.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.
Here I fix a minor bug affecting
MLP's output shape, after the PL 2.0 main update.The
MLPsolution involved a simple reshape of the final forward predictions.Additionally I noticed a similar validation memory error, with an entirely different origin for all
Recurrent-based models.The
Recurrent-based solution involved the addition of a newinference_input_sizeparameter that enables models to truncate the length of the series upon which they are applied to save computation and memory.