This repository was archived by the owner on Nov 17, 2023. It is now read-only.
[v1.x] ONNX Change some 10D shapes to 8D#20258
Merged
Zha0q1 merged 1 commit intoapache:v1.xfrom May 12, 2021
Merged
Conversation
|
Hey @Zha0q1 , Thanks for submitting the PR
CI supported jobs: [unix-gpu, centos-cpu, unix-cpu, sanity, website, miscellaneous, clang, edge, windows-cpu, centos-gpu, windows-gpu] Note: |
mseth10
added
the
pr-awaiting-testing
waytrue17
approved these changes
May 12, 2021
Contributor
waytrue17
left a comment
waytrue17
left a comment
There was a problem hiding this comment.
LGTM, thanks for the fix!
mseth10
added
pr-work-in-progress
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 subscribe to this conversation on GitHub.
Already have an account?
Sign in.
4 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
ONNX Transpose requires static permutations. So to do "dynamic transpose" we sometimes need to do a trick to reshape the input tensor to a known high dimension first, do transpose, and reshape back to lower dimension.
Previously I hardcoded the high dimension to be 10-D but some inference frameworks (including trt) only supports up to 8D. This pr changes those 10D shapes to 8D