Normal initialization

Fills the input Tensor with values drawn from the normal distribution

nn_init_normal_(tensor, mean = 0, std = 1)

Arguments

tensor	an n-dimensional Tensor
mean	the mean of the normal distribution
std	the standard deviation of the normal distribution

Examples

if (torch_is_installed()) {
w <- torch_empty(3, 5)
nn_init_normal_(w)

}
#> torch_tensor
#>  0.4278 -1.8461  0.2692 -0.4537  0.0622
#>  0.2497  2.2805 -0.2020  0.1530  0.0831
#>  0.8084 -0.4409  0.5042  1.3481 -1.2371
#> [ CPUFloatType{3,5} ]