Skip to content

[frontend][pytorch] Add a new test case for torch aten::fill_ operator implementation#12857

Merged
masahi merged 1 commit intoapache:mainfrom
oviazlo:torch-add-test-fill-operator
Sep 22, 2022
Merged

[frontend][pytorch] Add a new test case for torch aten::fill_ operator implementation#12857
masahi merged 1 commit intoapache:mainfrom
oviazlo:torch-add-test-fill-operator

Conversation

@oviazlo
Copy link
Contributor

@oviazlo oviazlo commented Sep 21, 2022

Add a new test case for torch aten::fill_ operator implementation.

This new test is testing a case of usage of a sequence of operators aten::div() and aten::fill_() that was causing a failure during the deployment of Mask R-CNN model (torchvision 0.13.0 version of the model).

Issue: #12844

@masahi
Copy link
Member

masahi commented Sep 21, 2022

You need to include my change in frontend/pytorch.py from #12844 as well.

@oviazlo oviazlo force-pushed the torch-add-test-fill-operator branch from 32278fd to a0636ff Compare September 21, 2022 19:12
@oviazlo
Copy link
Contributor Author

oviazlo commented Sep 21, 2022

Thanks for the comment. I have included yours changes as well to the PR.

…ing on the fill value.

Add new test case for torch aten::fill_ operator implementation.
@oviazlo oviazlo force-pushed the torch-add-test-fill-operator branch from a0636ff to d7c7966 Compare September 21, 2022 23:13
Copy link

@shingjan shingjan left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM. Thanks for sending this fix!

@masahi masahi merged commit 39f71ae into apache:main Sep 22, 2022
ghost pushed a commit to neo-ai/tvm that referenced this pull request Nov 6, 2022
…r implementation (apache#12857)

Fix aten::fill_ torch operator implementation by adding constant folding on the fill value.
Add new test case for torch aten::fill_ operator implementation.
xinetzone pushed a commit to daobook/tvm that referenced this pull request Nov 25, 2022
…r implementation (apache#12857)

Fix aten::fill_ torch operator implementation by adding constant folding on the fill value.
Add new test case for torch aten::fill_ operator implementation.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants