Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Fixes for Mask-RCNN conversion #654

Merged
merged 4 commits into from
May 28, 2020
Merged

Fixes for Mask-RCNN conversion #654

merged 4 commits into from
May 28, 2020

Conversation

lazarevevgeny
Copy link
Contributor

@lazarevevgeny lazarevevgeny commented May 28, 2020 •
edited
Loading

Description:

  • Added dependency for transformation of Mask-RCNN model to run before transformation for SoftMaxONNX
  • Added conversion of output from ExperimentalDetectronDetectionOutput with indices to i64 to be consistent with consumer of this output.
  • Fixed validate_and_infer_types for NMS ops.

Code:

  • Comments
  • Code style (PEP8)
  • Transformation generates reshape-able IR: N/A
  • Transformation preserves node names: N/A

Validation:

  • Unit tests: N/A
  • Framework layer tests: N/A
  • Transformation tests: N/A
  • e2e model test with an update of ./tests/e2e_oss/utils/reshape_utils.py: N/A not a new model
  • MO IR Reader check: N/A not a new model

Documentation:

  • Supported frameworks operations list: N/A
  • Supported public models list: N/A
  • New operations specification: N/A
  • Guide on how to convert the public model: N/A
  • User guide update: N/A

@lazarevevgeny lazarevevgeny changed the title Fixes for Mask-RCNN convertsion Fixes for Mask-RCNN conversion May 28, 2020
@lazarevevgeny lazarevevgeny marked this pull request as ready for review May 28, 2020 07:13
@lazarevevgeny lazarevevgeny requested review from a team May 28, 2020 07:13
jane-intel
jane-intel approved these changes May 28, 2020
View reviewed changes
Copy link
Contributor

@jane-intel jane-intel left a comment

Choose a reason for hiding this comment

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

LGTM

@lazarevevgeny lazarevevgeny merged commit 0efe474 into openvinotoolkit:master May 28, 2020
azhogov pushed a commit to azhogov/openvino that referenced this pull request Jun 1, 2020
@lazarevevgeny
Fixes for Mask-RCNN conversion (openvinotoolkit#654)
aea07a6 
* Fixed ONNX Mask-RCNN conversion

* Fixed validate_and_infet_types for NMS ops: added check for number of connected inputs

* Updated NMS ops to properly handle optional input with index 2

* Fixed typo in the implementation
@ilya-lavrenov ilya-lavrenov added the category: MO Model Optimizer label Jun 4, 2020
@ilya-lavrenov ilya-lavrenov added this to the 2020.4 milestone Jun 4, 2020
redradist pushed a commit to redradist/openvino that referenced this pull request Oct 6, 2023
@nkogteva
[NVIDIA] Revert disabling some tests due to cuda version update (open…
4c116a1 
…vinotoolkit#654)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jane-intel jane-intel jane-intel approved these changes

@GlebKazantaev GlebKazantaev GlebKazantaev approved these changes

Assignees

@jane-intel jane-intel

Labels
category: MO Model Optimizer
Projects
None yet
Milestone
2020.4
Development

Successfully merging this pull request may close these issues.
4 participants
@lazarevevgeny @GlebKazantaev @jane-intel @ilya-lavrenov