You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Currently, it does not support the function, but I'll add more efficient version soon.
For now, you can do the following. Make sure that the coordinates are non-negative when you create the sparse_input.
sparse_output=Network(sparse_input)
coordinates=sparse_output.Cout_size=coordinates.max(0)[0] +1# get the max indicesout_size=out_size.tolist() + [sparse_output.F.shape[1],]
dense_output=torch.zeros(out_size)
fori, coordinenumerate(coordinates):
dense_output[tuple(coord)] =sparse_output.F[i]
returndense_output
No description provided.
The text was updated successfully, but these errors were encountered: