Corrects resize validation for dynamic shapes #561
Merged
+54
−39
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
pranavm-nvidia
requested review from
christopherbate and
shelkesagar29
as code owners
pranavm-nvidia
force-pushed
the
fix-resize-checks
branch
2 times, most recently
from
7acb20a to
8bdf54f
Compare
When the output dimensions are dynamic and the `output_shape` parameter has not been provided, resize requires `scales` to be present. The previous checks were erroneously reporting errors if the input dimensions were dynamic, even though this is actually supported by TensorRT. Also cleans up several error messages to be clearer.
pranavm-nvidia
force-pushed
the
fix-resize-checks
branch
from
5866bb3 to
7ab2e51
Compare
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Outdated suggestions cannot be applied.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.
When the output dimensions are dynamic and the
output_shapeparameter has not been provided, resize requiresscalesto be present. The previous checks were erroneously reporting errors if the input dimensions were dynamic, even though this is actually supported by TensorRT.Also cleans up several error messages to be clearer.