KEMBAR78
Add mask target generator operator for Mask-RCNN by Kh4L · Pull Request #16268 · apache/mxnet · GitHub
Skip to content
This repository was archived by the owner on Nov 17, 2023. It is now read-only.

Add mask target generator operator for Mask-RCNN #16268

Merged
merged 3 commits into from
Oct 14, 2019
Merged

Add mask target generator operator for Mask-RCNN #16268

merged 3 commits into from
Oct 14, 2019

Conversation

@Kh4L
Copy link
Contributor

@Kh4L Kh4L commented Sep 25, 2019 •
edited
Loading

Description

Add mrcnn_target GPU operator.

It computes Mask-RCNN mask targets. It takes the same arguments and produces the same outputs as this Gluon block.

Micro-benchmark:

mrcnn_target operator 374ns vs Reference 5.43μs

Checklist

Essentials

Please feel free to remove inapplicable items for your PR.

  • Changes are complete (i.e. I finished coding on this PR)
  • All changes have test coverage:
  • Unit tests are added for small changes to verify correctness (e.g. adding a new operator)
  • Code is well-documented:
  • For user-facing API changes, API doc string has been updated.
  • For new C++ functions in header files, their functionalities and arguments are documented.
  • For new examples, README.md is added to explain the what the example does, the source of the dataset, expected performance on test set and reference to the original paper if applicable
  • To the my best knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change

Changes

  • Operator, tests, (and when applicable, API doc)

Comments

  • Add type support
  • Need to test Symbol API

@Kh4L
Add mask target generator operator for Mask-RCNN
4fd1f16 
Signed-off-by: Serge Panev <spanev@nvidia.com>
@Kh4L Kh4L force-pushed the mrcnn_mask_target_op branch from 7ebf042 to 4fd1f16 Compare September 25, 2019 14:20
@Kh4L
Disable the unit test for CPU default ctx
c02ec17 
Signed-off-by: Serge Panev <spanev@nvidia.com>
@anirudhacharya
Copy link
Member

Micro-benchmark:

mrcnn_target operator 374ns vs Reference 5.43μs

What is the reference in this benchmark?

@Jerryzcn
Copy link
Contributor

Micro-benchmark:

mrcnn_target operator 374ns vs Reference 5.43μs

What is the reference in this benchmark?

Probably the current python version

wkcn
wkcn reviewed Sep 25, 2019
View reviewed changes
@Kh4L
Copy link
Contributor Author

Kh4L commented Sep 25, 2019

mrcnn_target operator 374ns vs Reference 5.43μs

@anirudhacharya

@Jerryzcn is right, it is this Gluon code, hybridized.

@Kh4L
Address PR comments
14d0817 
Signed-off-by: Serge Panev <spanev@nvidia.com>
wkcn
wkcn approved these changes Sep 28, 2019
View reviewed changes
Copy link
Member

@wkcn wkcn left a comment

Choose a reason for hiding this comment

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

LGTM. Thank you!

@Kh4L Kh4L mentioned this pull request Oct 14, 2019
Merged
@zhreshold zhreshold merged commit 1d4ede3 into apache:master Oct 14, 2019
aaronmarkham pushed a commit to aaronmarkham/incubator-mxnet that referenced this pull request Oct 16, 2019
@Kh4L @aaronmarkham
Add mask target generator operator for Mask-RCNN (apache#16268)
a46218c 
* Add mask target generator operator for Mask-RCNN

Signed-off-by: Serge Panev <spanev@nvidia.com>

* Disable the unit test for CPU default ctx

Signed-off-by: Serge Panev <spanev@nvidia.com>

* Address PR comments

Signed-off-by: Serge Panev <spanev@nvidia.com>
apeforest pushed a commit that referenced this pull request Nov 14, 2019
@Kh4L @apeforest
Add mask target generator operator for Mask-RCNN (#16268)
89db058 
* Add mask target generator operator for Mask-RCNN

Signed-off-by: Serge Panev <spanev@nvidia.com>

* Disable the unit test for CPU default ctx

Signed-off-by: Serge Panev <spanev@nvidia.com>

* Address PR comments

Signed-off-by: Serge Panev <spanev@nvidia.com>
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Reviewers

2 more reviewers

@zhreshold zhreshold zhreshold approved these changes

@wkcn wkcn wkcn approved these changes

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

5 participants

@Kh4L @anirudhacharya @Jerryzcn @zhreshold @wkcn