Hi all,
Performing matrix multiplication between a sparse tensor and a dense one works well as in the documentation:
a = torch.randn(2, 3).to_sparse().requires_grad_(True)
b = torch.randn(3, 2, requires_grad=True)
y = torch.sparse.mm(a, b)
But when I try to do matrix multiplication between 2 sparse tensors, I obtain the error in title:
RuntimeError: s_native_addmm is not implemented for type torch.sparse.FloatTensor
a = torch.randn(2, 3).to_sparse().requires_grad_(True)
b = torch.randn(3, 2, requires_grad=True).to_sparse()
y = torch.sparse.mm(a, b)
Do you plan to implement this functionality? What would be a work around for this?
Thank you for your help in advance, have a good day!
Samuel