Advice
I want to find a convolutional network with a large kernel (larger than 5x5 or 7x7). I want to perform kernel analysis, and to do this, I need to convert the model to the onnx format. I found architectures with convolutions of size 51x51 (https://github.com/VITA-Group/SLaK), but I'm having trouble converting them to onnx. Can you recommend architectures with large kernels that can be converted to the onnx format?