Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Conversation

rogday
Copy link
Member

@rogday rogday commented Oct 17, 2022

Resolves #22623

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 another license that is incompatible with OpenCV
  • The PR is proposed to the proper branch
  • There is a reference to the 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

@rogday rogday added bug category: dnn (onnx) ONNX suport issues in DNN module labels Oct 17, 2022
testONNXModels("split_neg_axis");
}

// Mul inside with 0-d tensor, output should be A x 1, but is 1 x A.
Copy link
Member Author

Choose a reason for hiding this comment

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

Do we need to support such cases?

@asmorkalov
Copy link
Contributor

I still observe one test failure with my GF 1080, Cuda 10.2 and CuDNN 7.6.5. The same fault is visible on CI with removed suppression list.

[==========] Running 1 test from 1 test case.
[----------] Global test environment set-up.
[----------] 1 test from Test_ONNX_nets
[ RUN      ] Test_ONNX_nets.LResNet100E_IR/1, where GetParam() = CUDA/CUDA_FP16
/mnt/projects/Projects/OpenCV/opencv-master/modules/dnn/test/test_common.impl.hpp:74: Failure
Expected: (normL1) <= (l1), actual: 0.00869873 vs 0.008
  |ref| = 3.3252670764923096
[  FAILED  ] Test_ONNX_nets.LResNet100E_IR/1, where GetParam() = CUDA/CUDA_FP16 (2323 ms)
[----------] 1 test from Test_ONNX_nets (2323 ms total)

[----------] Global test environment tear-down
[==========] 1 test from 1 test case ran. (2323 ms total)
[  PASSED  ] 0 tests.
[  FAILED  ] 1 test, listed below:
[  FAILED  ] Test_ONNX_nets.LResNet100E_IR/1, where GetParam() = CUDA/CUDA_FP16

Copy link
Member

@fengyuentau fengyuentau left a comment

Choose a reason for hiding this comment

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

👍 LGTM

Copy link
Contributor

@asmorkalov asmorkalov left a comment

Choose a reason for hiding this comment

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

👍

@asmorkalov asmorkalov merged commit f378f02 into opencv:4.x Oct 19, 2022
@asmorkalov asmorkalov added this to the 4.7.0 milestone Oct 19, 2022
@rogday rogday deleted the cuda_test_fixes branch October 19, 2022 07:49
@alalek alalek mentioned this pull request Jan 8, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

bug category: dnn (onnx) ONNX suport issues in DNN module category: dnn

Projects

None yet

Development

Successfully merging this pull request may close these issues.

DNN test failures with CuDNN support

4 participants