onnx frontend support layout choice depend on hardware target supported layout with NCHW and NHWC#4474
Closed
Beya2019 wants to merge 2 commits into
Closed
onnx frontend support layout choice depend on hardware target supported layout with NCHW and NHWC#4474Beya2019 wants to merge 2 commits into
Beya2019 wants to merge 2 commits into
Conversation
…ed layout with NCHW and NHWC
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 submission adds a feature that onnx frontend support layout choice with NCHW and NHWC depended on hardware target supported layout . Now every frontend framework does not support layout choice depend. Such as, relay.frontend.from_onnx only support NCHW and relay.frontend.from_tensorflow only support NHWC. Given that TVM is supported NCHW and NHWC,
and if our target hardware support NHWC, we should add NHWC layout in onnx frontend to produce the NHWC graph and finally compute on the target hardware.
@vinx13 would you be able to take a look?