Fills the input Tensor or Variable with a (semi) orthogonal matrix, as described in “Exact solutions to the nonlinear dynamics of learning in deep linear neural networks” - Saxe, A. et al. (2013). The input tensor must have at least 2 dimensions, and for tensors with more than 2 dimensions the trailing dimensions are flattened.

Examples

>>> w = torch.Tensor(3, 5)
>>> nn.init.orthogonal(w)