tensorplay.nn.init.orthogonal_

tensorplay.nn.init.orthogonal_(tensor, gain=1, generator=None)[source]

Fill tensor in-place with a (semi) orthogonal matrix.

The tensor must have at least 2 dimensions; trailing dimensions are flattened. Rows (or columns, when narrower) are orthonormalized with a QR factorization of a standard-normal sample, and Q is rescaled by the diagonal signs of R so its distribution is uniform over the orthogonal group.