This repository has been archived by the owner on Nov 16, 2023. It is now read-only.
Support super resolution models and benchmarking #291
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
duli2012
reviewed
Apr 27, 2021
| @@ -0,0 +1,5 @@ | |||
| # Licenses | |||
There was a problem hiding this comment.
should this be license or readme?
There was a problem hiding this comment.
Since we put tfjs in our benchmark, we need to specify tfjs's license here to state that we are using some other project. I think i included a README in the same folder.
| @@ -0,0 +1,38 @@ | |||
| # Benchmarks | |||
There was a problem hiding this comment.
could we generalize this sub project to other models besides SR, which would be very useful feature?
There was a problem hiding this comment.
Yes i put a TODO in the main index.js file to improve this benchmark to take arbitrary models and configs. For that, we would need a benchmark driver similar to our test-runner-cli. I will do a followup change just for the benchmarking tool.
added 7 commits
May 6, 2021 13:41
depth-to-space kernel bug fixes
migrating this to the new repo...
Tixxx
changed the title
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
This PR adds the following support:
depth to space kernel to run office super resolution model
6d tensor support in coordinate library to run model zoo super resolution
a super resolution benchmarking tool that compares the performance of onnxjs to the latest tfjs with profiling info.
This pr also exposes a logger config(only contains a log level field) to the inference session so that logger's log level can be configured from onnxjs api.
***All the required changes are verified currently. This PR is for viewing diffs only. Changes are being migrated to the new ORT repo.