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.

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

Implement LookupTableInsert shape inference #2348

Merged

Conversation

rkazants
Copy link
Contributor

@rkazants rkazants commented Sep 21, 2020

Description: In some OCR model Nodes not being pruned in a graph have a conditional dependence on LookupTableInsert node and it requires a shape inference for this node before conditional resolving pass.

JIRA: 38082

Code:

  • Comments
  • Code style (PEP8)
  • Transformation generates reshape-able IR - N/A. it does not introduce new transformations
  • Transformation preserves original framework node names - N/A. it does not introduce new transformations

Validation:

  • Unit tests
  • Framework operation tests - N/A. it does not implement any framework operations
  • Transformation tests - N/A
  • e2e model test with an update of ./tests/e2e_oss/utils/reshape_utils.py - it will be in a separate ticket
  • Model Optimizer IR Reader check

Documentation:

  • Supported frameworks operations list - it does not introduce new operations in out opset
  • Supported public models list - it is not a public model
  • New operations specification - it does not introduce new operations in out opset
  • Guide on how to convert the public model - it is not a public model
  • User guide update - it is not a public model

Signed-off-by: Roman Kazantsev [email protected]

@rkazants rkazants requested a review from a team September 21, 2020 10:18
@openvino-pushbot openvino-pushbot added the category: MO Model Optimizer label Sep 21, 2020
@rkazants rkazants requested review from mvafin and achetver September 21, 2020 10:27
@rkazants rkazants force-pushed the feature/rkazants/ocr_model branch from 939dbb2 to 657d981 Compare September 22, 2020 07:18
@rkazants rkazants requested a review from jane-intel September 22, 2020 07:19
Copy link
Contributor

@achetver achetver left a comment

Choose a reason for hiding this comment

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

These changes looks good to me.

@lazarevevgeny
Copy link
Contributor

@rkazants , do you plan to resolve these comments?

@rkazants rkazants force-pushed the feature/rkazants/ocr_model branch from 657d981 to 85edab4 Compare October 16, 2020 16:25
It is needed if other nodes not beeing pruned in the graph
have a conditional dependence on LookupTableInsertV2 node.

Signed-off-by: Roman Kazantsev <[email protected]>
Signed-off-by: Roman Kazantsev <[email protected]>
Signed-off-by: Roman Kazantsev <[email protected]>
@rkazants rkazants force-pushed the feature/rkazants/ocr_model branch from d7129ae to 301b6cd Compare October 19, 2020 06:22
@rkazants
Copy link
Contributor Author

@rkazants , do you plan to resolve these comments?

Resolved.

@rkazants rkazants changed the title Implement LookupTableInsertV2 shape inference Implement LookupTableInsert shape inference Oct 19, 2020
@lazarevevgeny lazarevevgeny merged commit c239450 into openvinotoolkit:master Oct 20, 2020
mryzhov pushed a commit to mryzhov/openvino that referenced this pull request Dec 16, 2020
* Implement LookupTableInsertV2 shape inference

It is needed if other nodes not beeing pruned in the graph
have a conditional dependence on LookupTableInsertV2 node.

Signed-off-by: Roman Kazantsev <[email protected]>

* Fix after core-review #1

Signed-off-by: Roman Kazantsev <[email protected]>

* Fix the code after review #2

Signed-off-by: Roman Kazantsev <[email protected]>

* Fix after code review #3
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
category: MO Model Optimizer
Projects
None yet
Development

Successfully merging this pull request may close these issues.

6 participants