openvino
openvino copied to clipboard
openvinotoolkit
[GoodFirstIssue][OP CONFORMANCE][TEMPLATE] Added static shape generator for dynamic shapes
Details:
- Added generator of static shapes based on an operation type.
Tickets:
- https://github.com/openvinotoolkit/openvino/issues/23551
@Vladislav-Denisov Many thanks for investigation and contribution to OpenVINO! Welcome to our project!
As I can see, we have two similar PR for two contributors: PR from @Vladislav-Denisov and PR from @awayzjj. So the main difference is fix static input static shape generation for different operations: first PR is for pooling ops, second one is for convolution.
The possible option is to merge 2 solution to one and develop static input generation for pooling and convolution over the solution. Second option is to merge first green PR with applied review comments as a source solution for input static shape generation, second PR should be based on first merged.
@Vladislav-Denisov @awayzjj Please discuss in PR comments?
FYI: Each of @Vladislav-Denisov @awayzjj will be a contributor to OpenVino. We need to decide merge order and align the solutions.
Many thanks! So sorry for inconvenience
@Vladislav-Denisov Many thanks for investigation and contribution to OpenVINO! Welcome to our project!
As I can see, we have two similar PR for two contributors: PR from @Vladislav-Denisov and PR from @awayzjj. So the main difference is fix static input static shape generation for different operations: first PR is for pooling ops, second one is for convolution.
The possible option is to merge 2 solution to one and develop static input generation for pooling and convolution over the solution. Second option is to merge first green PR with applied review comments as a source solution for input static shape generation, second PR should be based on first merged.
@Vladislav-Denisov @awayzjj Please discuss in PR comments?
FYI: Each of @Vladislav-Denisov @awayzjj will be a contributor to OpenVino. We need to decide merge order and align the solutions.
Many thanks! So sorry for inconvenience
I would prefer the second option. In my opinion, this looks more correct. @awayzjj what do you think?
@Vladislav-Denisov Many thanks for investigation and contribution to OpenVINO! Welcome to our project! As I can see, we have two similar PR for two contributors: PR from @Vladislav-Denisov and PR from @awayzjj. So the main difference is fix static input static shape generation for different operations: first PR is for pooling ops, second one is for convolution. The possible option is to merge 2 solution to one and develop static input generation for pooling and convolution over the solution. Second option is to merge first green PR with applied review comments as a source solution for input static shape generation, second PR should be based on first merged. @Vladislav-Denisov @awayzjj Please discuss in PR comments? FYI: Each of @Vladislav-Denisov @awayzjj will be a contributor to OpenVino. We need to decide merge order and align the solutions. Many thanks! So sorry for inconvenience
I would prefer the second option. In my opinion, this looks more correct. @awayzjj what do you think?
I agree with you.
@Vladislav-Denisov @awayzjj Please check the comments under each of your PRs.
Many thanks!
@iefode I have added new fixes and improvements. Could you please review again?
@Vladislav-Denisov FYI Your PR is failed on Op conformance run over CPU. This run uses the same same infra as your PR, but the backend is different (CPU vs TEMPLATE)
@iefode I rebased to the latest master branch state and added my changes for MaxPool. Could you review one more time please?