Skip to contents

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.

Usage

nn_init_orthogonal_(tensor, gain = 1)

Arguments

tensor

an n-dimensional Tensor

gain

optional scaling factor

Examples

if (torch_is_installed()) {
w <- torch_empty(3, 5)
nn_init_orthogonal_(w)
}
#> torch_tensor
#>  0.3225 -0.6461  0.4096  0.0415 -0.5559
#>  0.4231 -0.4908 -0.7005 -0.0313  0.2975
#> -0.2485 -0.4405  0.4623 -0.2294  0.6913
#> [ CPUFloatType{3,5} ]