Support NPU for SSD MobileNetV1 example #228
Merged
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
This change converts the float32 weigths to float16 at loading time. And it uses WebNN cast operator to convert float32 inputs to float16 before compute and convert float16 outputs back to float32 after compute.
Honry
reviewed
May 5, 2024
There was a problem hiding this comment.
@huningxin, thanks for the PR! Good idea to cast the float 32 to float 16 directly for NPU, maybe we can support fp16 in other samples like this if there's no precision issue.
Honry
pushed a commit
to Honry/webnn-samples
that referenced
this pull request
May 15, 2024
* Support NPU for SSD MobileNetV1 example This change converts the float32 weigths to float16 at loading time. And it uses WebNN cast operator to convert float32 inputs to float16 before compute and convert float16 outputs back to float32 after compute. * Fix lint error
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Outdated suggestions cannot be applied.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.
This change converts the float32 weigths to float16 at loading time. And it uses WebNN cast operator to convert float32 inputs to float16 before compute and convert float16 outputs back to float32 after compute.
/cc @mingmingtasd @ibelem