I can ONNX export the pytorch model created with the notebook file at [login to view URL] But the ONNX model created here only contains feature maps and what I want is to create an interpreter with dynamic input and output working with OpenCV in C++.
I prefer it to work with opencv dnn module. But onnxruntime can also use.
Please take a look at the files I uploaded before applying.
I can give 2 days as the completion time. Anyone who can do this project should have it done in 1-2 days at the most.