register batchnorm for opset14 cuda provider#7806
Merged
Merged
Conversation
SherlockNoMad
approved these changes
May 24, 2021
| BatchNormalization, \ | ||
| kOnnxDomain, \ | ||
| 9, \ | ||
| 14, \ |
Member
There was a problem hiding this comment.
It looks like this kernel registration has a small bug. Opset-14 introduced a new type constraint 'U' for mean/var. The implementation only supports cases where T == U. For T != U cases, it will crash within the kernel when we reference data of type T for the inputs containing type U. I guess we need to add .TypeConstraint("U",DataTypeImpl::GetTensorType<T>()) here.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description: Register batch norm opset 14 for cuda provider
Motivation and Context