Hi,
I’m learning to use opencv and trying to run the sample from opencv repo but it always throws an exception. I have no idea how to debug it.
What I tried is to follow this tutorial OpenCV: Load Caffe framework models
and use the exact code from the repo: https://github.com/opencv/opencv/blob/4.x/samples/dnn/classification.cpp
The model/config/classes are downloaded according to the tutorial
download GoogLeNet model files: bvlc_googlenet.prototxt and bvlc_googlenet.caffemodel
Also you need file with names of ILSVRC2012 classes: classification_classes_ILSVRC2012.txt.
I compile it using this command
g++ classification.cpp -o classification -lopencv_core -lopencv_imgproc -lopencv_imgcodecs -lopencv_highgui -lopencv_dnn -lopencv_videoio
and run it like
./classification --model=bvlc_googlenet.caffemodel --config=bvlc_googlenet.prototxt --width=224 --height=224 --classes=classification_classes_ILSVRC2012.txt --mean="104 117 123" --rgb=false --input=space_shuttle.jpg
But when I run it, I always get the exception
$ ./classification --model=bvlc_googlenet.caffemodel --config=bvlc_googlenet.prototxt --width=224 --height=224 --classes=classification_classes_ILSVRC2012.txt --mean="104 117 123" --rgb=false --input=space_shuttle.jpg
mean: [104, 117, 123, 0]
std: [0, 0, 0, 0]
Authorization required, but no authorization protocol specified
Authorization required, but no authorization protocol specified
Qt: Session management error: Could not open network socket
terminate called after throwing an instance of 'cv::Exception'
what(): OpenCV(4.7.0) /home/abuild/rpmbuild/BUILD/opencv-4.7.0/modules/dnn/src/layers/fast_convolution/winograd_3x3s1_f63.cpp:147: error: (-215:Assertion failed) _FX_WINO_IBLOCK == 3 && _FX_WINO_KBLOCK == 4 in function '_fx_winograd_accum_f32'
Aborted (core dumped)
I’m using the library version 4.7.0 from OpenSUSE TumbleWeed. I’m new to OpenCV. And don’t know how to debug OpencV specific application (I know debugging in general). Can anybody help me to understand what’s happening and how to solve it?
Thanks so much.