ZzTodd22

Can sparse convolution benefit from the pre-existing weights of dense convolution?

1

Thank you immensely for sharing your work! I do have a query though: I've transitioned an identical model from dense convolution to sparse convolution. Despite meticulously loading the weights of...

Here is my code: ``` def BasicConv3d(in_planes, out_planes, kernel_size, stride=(1, 1, 1), padding=(0, 0, 0), bias=False, convstyle='SubMConv3d'): """3x3 convolution with padding""" if convstyle=='SparseConv3d': return spconv.SparseConv3d(in_planes, out_planes, kernel_size=kernel_size, stride=stride, padding=padding, bias=bias)...