Failed to load pre trained onnx models

C++
,
1

This is my first time with ONNX models and I’m not sure if I’m having a newbie problem so sorry in advance!

I’ve just tried to load a couple of models and I have the same assert always:


[ERROR:0@0.460] global onnx_importer.cpp:1054 cv::dnn::dnn4_v20221220::ONNXImporter::handleNode DNN/ONNX: ERROR during processing node with 3 inputs and 1 outputs: [Concat]:(onnx_node!Concat_2) from domain='ai.onnx'
OpenCV: terminate handler is called! The last OpenCV error is:
OpenCV(4.7.0-dev) Error: Unspecified error (> Node [Concat@ai.onnx]:(onnx_node!Concat_2) parse error: OpenCV(4.7.0-dev) C:\GHA-OCV-2\_work\ci-gha-workflow\ci-gha-workflow\opencv\modules\dnn\src\layers\concat_layer.cpp:105: error: (-215:Assertion failed) curShape.size() == outputs[0].size() in function 'cv::dnn::ConcatLayerImpl::getMemoryShapes'
> ) in cv::dnn::dnn4_v20221220::ONNXImporter::handleNode, file C:\GHA-OCV-2\_work\ci-gha-workflow\ci-gha-workflow\opencv\modules\dnn\src\onnx\onnx_importer.cpp, line 1073

Both models come from GitHub - PeterL1n/RobustVideoMatting: Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
and they are “rvm_resnet50_fp32.onnx” and “rvm_mobilenetv3_fp32.onnx”

Obviously I’m loading them with
robustNN = cv::dnn::readNetFromONNX(robustNNPath);

Thank you in advance for any tip!

1 Like
2

undeclared crosspost:

(includes debate on crossposting and declaring)

3

definitely not so !
did you make any progress with it ?

sadly, the error you get, might be just the ‘tip-of-the-iceberg’, looking at the model, i also foud gru and hardswish layers, all unsupported here ;(