OpenCv can't load and read Yolov7 Onnx format

I am trying to read and load a Yolov7 torch onnx model using OpenCV but it shows this error and I wasn’t able to fix it.

error: OpenCV(4.6.0) /io/opencv/modules/dnn/src/onnx/onnx_importer.cpp:1040: error: (-2:Unspecified error) in function 'handleNode'
> Node [Mul@ai.onnx]:(onnx_node!Mul_329) parse error: OpenCV(4.6.0) /io/opencv/modules/dnn/src/onnx/onnx_importer.cpp:2221: error: (-213:The function/feature is not implemented) Different shapes case is not supported with constant inputs: Mul in function 'parseMul'
>

please try with current 4.8.1 instead

please show torch export code

I use this lines of code to convert torch to onnx

dummy_input = torch.randn(N, 3, H, W, device="cpu")
input_names = [ "images" ]
output_names = [ "output1" ]
torch.onnx.export(model, dummy_input, "Yolov7.onnx", verbose=False, input_names=input_names, output_names=output_names, opset_version = 11)```