| CARVIEW |
Navigation Menu
-
-
Notifications
You must be signed in to change notification settings - Fork 56.2k
DNN/CUDA: Solve the bug of same shape broadcast with CUDA #23560
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
Conversation
WanliZhong
added
bug
category: gpu/cuda (contrib)
|
@peters Hi, could you help to test if this pr will run yolov7-tiny correctly mentioned in e3e1f70#commitcomment-110475963? Thanks! |
DNN/CUDA: make 'abcd op 1b11' broadcast eltwise operator support cuda
|
@WanliZhong This PR fixes the yolov7-tiny inference problem. All tests are now green on our side! Thank you :) |
|
@peters That's good! Thanks! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM! đź‘Ť
zihaomu
added
test
and removed
pr: needs test
|
Test results after merged PR #23557 and this PR |
|
Lets re-enable disabled tests. They are fine on CPU target and pass on CUDA target (but they are slow in the current implementation). On CUDA target they could be skipped (if performance is critical) in this way: or To manually run "skipped" tests by tags add this option: |
|
Thanks @opencv-alalek ! I will enable it. |
WanliZhong
force-pushed
the
eltwise_cuda_bug
branch
from
4083096 to
80045b5
Compare
WanliZhong
force-pushed
the
eltwise_cuda_bug
branch
from
80045b5 to
46991bc
Compare
|
@opencv-alalek All tests are green. Should I merge with enabled or disabled brute-force tets? |
| @@ -1949,6 +1949,9 @@ struct Layer_Test_Eltwise_bcast : testing::TestWithParam<tuple<string, int, tupl | |||
| int backend = get<0>(backend_target); | |||
| int target = get<1>(backend_target); | |||
|
|
|||
| if (backend == DNN_BACKEND_CUDA && dim > 4) | |||
| applyTestTag(CV_TEST_TAG_LONG); | |||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
BTW, Looks like no tests are skipped on CI.
CV_TEST_TAG_VERYLONG tests are skipped by default.
CV_TEST_TAG_LONG tests should be skipped on embedded platforms or coverage/valgrind build configurations (though extra parameter on CI).
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Longer than 5s but less than 20s, so it should use LONG tag
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Ok, lets run all CUDA tests.
Merged after #23557
Fix yolo regression error mentioned in e3e1f70#commitcomment-110475963
After fix this bug, the brute force test mentioned in #23556 will all passed with CUDA. (different shape broadcast will fallback to cpu)
Test is added in PR #23557
Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
Patch to opencv_extra has the same branch name.