Make denoising deterministic and speed it up #968
Merged
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
tongtongcao
requested review from
baltzell,
c-dilks and
raffaelladevita
as code owners
Collaborator
|
What's the speed for the c++ denoiser? |
baltzell
changed the title
Collaborator
Author
About 150 ms/event/thread |
Collaborator
|
FYI, here's the coatjava gitlab "model registry", started playing with it just now and we should switch to it for the next network: |
Collaborator
|
Or, rather, let's use another git repo for now, see #970. |
baltzell
changed the title
baltzell
changed the title
Collaborator
|
Note it's still looping over the input (and output) bank 6 times, before constructing the batch. |
baltzell
approved these changes
Dec 3, 2025
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Outdated suggestions cannot be applied.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.
To avoid random behavior when application of model, the origin model, saved by torch.jit.trace is replaced by the model, saved by torch.jit.script.
The engine is updated to process 6 sectors as batch. Also, translator for input and output of the model is updated.
As test in clara workflow, run time is improved from ~150 ms/event/thread to ~90 ms/event/thread.