Fills the input Tensor 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
if (torch_is_installed()) {
w <- torch_empty(3, 5)
nn_init_orthogonal_(w)
}
#> torch_tensor
#> -0.0502 0.3716 0.1732 0.6357 0.6521
#> -0.6052 0.3074 -0.7232 -0.1048 0.0726
#> 0.4706 0.8246 -0.0229 -0.2610 -0.1731
#> [ CPUFloatType{3,5} ]