Improved edge detection sample#25515
Conversation
Other changes related to findFile and findModel will be added once classification sample pull request is approved and merged |
|
|
Looks like the model cannot be downloaded with download_models.py. I downloaded it manually and dnn path leads to crash: |
| { | ||
| CV_Assert(src.getObj() != dst.getObj()); | ||
| CV_Check(axis, axis >= 0 && axis < src.dims(), "Axis out of range"); | ||
| CV_Check(axis, axis >= 0 && (axis < src.dims() || (src.dims()==1 && axis==1)), "axis is out of range"); |
There was a problem hiding this comment.
src.dims()==1 && axis==1
It does not look valid to me for the general cases.
There was a problem hiding this comment.
@fengyuentau, yes, this is hack, because the generated model contains incorrect, out-of-range axis specification. The script needs to be fixed and then dexined model should be regenerated
There was a problem hiding this comment.
Ok, then @gursimarsingh could you add a comment for this?
|
@asmorkalov, let's finally merge it |
fengyuentau
left a comment
There was a problem hiding this comment.
In the meantime, please take a look at my comment in the PR in model zoo: opencv/opencv_zoo#272 (review)
#25006 #25314
This pull request removes hed_pretrained caffe model to the SOTA dexined onnx model for edge detection. Usage of conventional methods like canny has also been added
The obsolete cpp and python sample has been removed
TODO:
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.