int32 pooling with int64 shapes #6687
Merged
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
mbrookhart
changed the title
junrushao
approved these changes
Oct 14, 2020
tqchen
approved these changes
Oct 14, 2020
tmoreau89
approved these changes
Oct 14, 2020
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Oct 29, 2020
* Failing tests for Int32 avg_pooling with Int64 shapes * fix pooling implementations
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Dec 2, 2020
* Failing tests for Int32 avg_pooling with Int64 shapes * fix pooling implementations
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Dec 4, 2020
* Failing tests for Int32 avg_pooling with Int64 shapes * fix pooling implementations
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Dec 4, 2020
* Failing tests for Int32 avg_pooling with Int64 shapes * fix pooling implementations
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Outdated suggestions cannot be applied.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.
We found some quantized models that were performing Int32 average pooling with input tensors that had Int64 shapes. This caused an error in te where the resulting computations were implicitly up cast from int32 to int64 due to the way the topi functions were handling input shapes.
This PR adds unit tests that hit the error and provides fixes for the currently implemented ops.
@tmoreau89 @jwfromm @junrushao1994