Fix upsample half pixel mode for size one#2918
Open
PrithviBadiga wants to merge 1 commit into
Open
Conversation
Author
|
@microsoft-github-policy-service agree |
Author
@microsoft-github-policy-service agree |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes the ATen upsampling lowering for
align_corners=Falseto use ONNXhalf_pixelmode instead ofpytorch_half_pixel.pytorch_half_pixelspecial-cases output size 1 differently from PyTorch eager behavior, causing mismatches for cases likeupsample_bilinear2d(..., output_size=(1, 1), align_corners=False). This change makes the exportedResizenode match PyTorch results for that edge case.Adds regression samples for 2D upsampling with output size 1, covering both
upsample_bilinear2dandupsample_bilinear2d.vec.