Incorrect output after GPU to GPU inference via VideoFrame and Gray8 models #10425
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
smk2007
requested review from
martinb35,
ryanlai2,
tiagoshibata,
zhangxiang1993,
nums11,
linnealovespie and
fdwr
ryanlai2
previously approved these changes
Jan 28, 2022
fdwr
reviewed
Jan 28, 2022
…eing compared to constant and not DXGI_FORMAT
fdwr
approved these changes
Jan 28, 2022
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Outdated suggestions cannot be applied.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.
Issue: The detensorization pipeline incorrectly interpreted Gray8 outputs as BGR8 outputs, and so detensorization was calling into incorrect shaders for conversion back from NCHW to NHWC.
Related Issues:
#10410 : [WinML] [C++/WinRT] Empty output after GPU to GPU inference via VideoFrame
Models which produce 1 channel (Gray8) format outputs fail to produce correct output when binding output VideoFrames that are D3D11 backed surfaces.
Fix: When the output tensor is marked as Gray8, honor the format (which calls the appropriate shader later on).