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
I don't understand how the last line code produces the symmetric matrix.
And I think it is intuitive to build the symmetric like this adj = adj + adj.T
Can anyone help to answer my questions? thanks a lot
The text was updated successfully, but these errors were encountered:
ok now I understand. the multiply is a point-wise multiplication, not a matrix product.
Hi, mate. I have the same problem here. I'm curious why we have to subtract adj.multiply(adj.T > adj)? Entries in adj.multiply(adj.T > adj) should be all zeros.
ok now I understand. the multiply is a point-wise multiplication, not a matrix product.
Hi, mate. I have the same problem here. I'm curious why we have to subtract adj.multiply(adj.T > adj)? Entries in adj.multiply(adj.T > adj) should be all zeros.
` adj = sp.coo_matrix((np.ones(edges.shape[0]), (edges[:, 0], edges[:, 1])),
shape=(labels.shape[0], labels.shape[0]),
dtype=np.float32)
I don't understand how the last line code produces the symmetric matrix.
And I think it is intuitive to build the symmetric like this
adj = adj + adj.T
Can anyone help to answer my questions? thanks a lot
The text was updated successfully, but these errors were encountered: