Dear author, excellent work!
I would like to know whether MinkowskiConvolution can modify the weights of the convolution like PyTorch., e.g. calling nn.F：
`torch.nn.functional.conv2d(input, weight, bias=None, stride=1, padding=0, dilation=1, groups=1) the docs
This would pass in custom weights(filters) for it, if so, where should I look for the code and modify it?
I hope you can get back to me, thanks!
If my question wasn't clear, I'll go back and describe it in more detail, and I appreciate your response.
Dear author, excellent work! I would like to know whether MinkowskiConvolution can modify the weights of the convolution like PyTorch., e.g. calling nn.F： `torch.nn.functional.conv2d(input, weight, bias=None, stride=1, padding=0, dilation=1, groups=1) the docs This would pass in custom weights(filters) for it, if so, where should I look for the code and modify it?
I hope you can get back to me, thanks! If my question wasn't clear, I'll go back and describe it in more detail, and I appreciate your response.