image_classification_mobilenet: cannot load models

[ukoehler]

Hi, I have been playing round with the model examples provided and face_detection_yunet and human_segmentation_pphumanseg worked quite well.

I am using an up-to-date version of the opencv_zoo and OpenCV4.5.5 installed via pip on Windows

When running the demo.py example for image_classification_mobilenet I get the following error for all models, however

[ERROR:0@0.089] global D:\a\opencv-python\opencv-python\opencv\modules\dnn\src\o
nnx\onnx_importer.cpp (909) cv::dnn::dnn4_v20211220::ONNXImporter::handleNode DN
N/ONNX: ERROR during processing node with 3 inputs and 1 outputs: [Clip]:(317) f
rom domain='ai.onnx'
Traceback (most recent call last):
File "D:\Local\devel\Python\OpenCV\image_classification_mobilenet\demo.py", li
ne 41, in
'v2': MobileNetV2(modelPath='./image_classification_mobilenetv2_2022apr.onnx
', labelPath=args.label, backendId=args.backend, targetId=args.target),
File "D:\Local\devel\Python\OpenCV\image_classification_mobilenet\mobilenet_v2
.py", line 11, in init
self.model = cv.dnn.readNet(self.model_path)
cv2.error: OpenCV(4.5.5) D:\a\opencv-python\opencv-python\opencv\modules\dnn\src
\onnx\onnx_importer.cpp:928: error: (-2:Unspecified error) in function 'cv::dnn:
:dnn4_v20211220::ONNXImporter::handleNode'

Node [Clip@ai.onnx]:(317) parse error: OpenCV(4.5.5) D:\a\opencv-python\opencv
-python\opencv\modules\dnn\src\onnx\onnx_importer.cpp:1613: error: (-2:Unspecifi
ed error) in function 'void __cdecl cv::dnn::dnn4_v20211220::ONNXImporter::parse
Clip(class cv::dnn::dnn4_v20211220::LayerParams &,const class opencv_onnx::NodeP
roto &)'

(expected: 'node_proto.input_size() == 1'), where
'node_proto.input_size()' is 3
must be equal to
'1' is 1

Can anybody point me to a solution, please?

[ukoehler]

Hmmm, I finally setup a different venv with onnx and
onnx.checker.check_model
shows that the model is valid. This looks decidedly like an OpenCV bug.

[fengyuentau]

Hello @ukoehler , models in opencv_zoo have been well tested on Linux. We will try to reproduce your issue on Windows.

[ukoehler]

Hi @fengyuentau, I managed to re-write the example to use OpenCV for image preparation and onnx runtime for model execution. That works quiet well. The model is not the problem, but the reading by OpenCV. I will submit a new bug there.

[fengyuentau]

This issue is fixed at opencv/opencv#22100, get the nightly OpenCV and it should work well.