Skip to content

[G-API] Prohibit setPrecision & preprocessing for importedNetworks#20528

Merged
alalek merged 4 commits intoopencv:masterfrom
TolyaTalamanov:at/fix-overwrite-blob-precision-bug
Aug 18, 2021
Merged

[G-API] Prohibit setPrecision & preprocessing for importedNetworks#20528
alalek merged 4 commits intoopencv:masterfrom
TolyaTalamanov:at/fix-overwrite-blob-precision-bug

Conversation

@TolyaTalamanov
Copy link
Copy Markdown
Contributor

Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

  • I agree to contribute to the project under Apache 2 License.
  • To the best of my knowledge, the proposed patch is not based on a code under GPL or other license that is incompatible with OpenCV
  • The PR is proposed to proper branch
  • There is reference to original bug report and related work
  • There is accuracy test, performance test and test data in opencv_extra repository, if applicable
    Patch to opencv_extra has the same branch name.
  • The feature is well documented and sample code can be built with the project CMake

Build configuration

force_builders=Custom,Custom Win,Custom Mac
build_gapi_standalone:Linux x64=ade-0.1.1f
build_gapi_standalone:Win64=ade-0.1.1f
build_gapi_standalone:Mac=ade-0.1.1f
build_gapi_standalone:Linux x64 Debug=ade-0.1.1f

Xbuild_image:Custom=centos:7
Xbuildworker:Custom=linux-1
build_gapi_standalone:Custom=ade-0.1.1f

build_image:Custom=ubuntu-openvino-2021.3.0:20.04
build_image:Custom Win=openvino-2021.2.0
build_image:Custom Mac=openvino-2021.2.0

test_modules:Custom=gapi,python2,python3,java
test_modules:Custom Win=gapi,python2,python3,java
test_modules:Custom Mac=gapi,python2,python3,java

buildworker:Custom=linux-1
# disabled due high memory usage: test_opencl:Custom=ON
test_opencl:Custom=OFF
test_bigdata:Custom=1
test_filter:Custom=*

@TolyaTalamanov TolyaTalamanov force-pushed the at/fix-overwrite-blob-precision-bug branch from 94b023e to dd49b8d Compare August 9, 2021 12:35
input_names -> output_names
@TolyaTalamanov
Copy link
Copy Markdown
Contributor Author

@mpashchenkov Could you have a look ?

Copy link
Copy Markdown
Contributor

@mpashchenkov mpashchenkov left a comment

Choose a reason for hiding this comment

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

Good for me. Thanks.

@TolyaTalamanov TolyaTalamanov requested a review from rgarnov August 13, 2021 13:30
@dmatveev dmatveev self-assigned this Aug 13, 2021
@dmatveev dmatveev added this to the 4.5.4 milestone Aug 13, 2021
Copy link
Copy Markdown
Contributor

@dmatveev dmatveev left a comment

Choose a reason for hiding this comment

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

LGTM (didn't check every line though), will our vpu camera cases continue working after these changes (where the blobs are imported and have to consume NV12 so the preprocessing is enabled in that case)?

uu.params.layer_names_to_reshape.end()) {
configureInputReshapeByImage(ii, mm, input_reshape_table);
// NB: Configuring input precision and network reshape must be done
// only for loadNetwork way.
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

only in the LoadNetwork case is maybe a better wording

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

Done

@alalek alalek merged commit 9591905 into opencv:master Aug 18, 2021
@alalek alalek mentioned this pull request Oct 15, 2021
a-sajjad72 pushed a commit to a-sajjad72/opencv that referenced this pull request Mar 30, 2023
…blob-precision-bug

[G-API] Prohibit setPrecision & preprocessing for importedNetworks

* Prohibit preprocessing for imported networks

* Fix typo

input_names -> output_names

* Move setBlob logic to separate function

* Change comment
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants