Fix recurrent block memory leak and output shape calculation #556
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
lanking520
reviewed
Jan 25, 2021
frankfliu
reviewed
Jan 25, 2021
stu1130
approved these changes
Jan 25, 2021
There was a problem hiding this comment.
Hi @mpskowron Thanks for your contribution. I am also doing refactoring on the model to make it more generic for latter PyTorch & TensorFlow integration. So I am going to merge your PR and rebase onto it.
frankfliu
approved these changes
Jan 25, 2021
|
Sounds great! Thank you guys for a quick review. |
Lokiiiiii
pushed a commit
to Lokiiiiii/djl
that referenced
this pull request
Oct 10, 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Outdated suggestions cannot be applied.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.
Description
opInputs(...)function, line 240:parameterList.add(array.flatten());array.flatten()is creating new array in model's NDManager, thus this array lives as long as the model. The analogical problem is also present in LSTM block.getOutputShapes(...)function returns incorrect shapes. Block accepts NTC not TNC (which is wrongly assumed as input shape ingetOutputShapes(...)function).