Random normal

Returns a tensor filled with random numbers from a normal distribution with mean 0 and variance 1 (also called the standard normal distribution).

tch_randn(sizes, dtype = NULL, layout = NULL, device = NULL,
  requires_grad = FALSE)

Arguments

sizes	a sequence of integers defining the shape of the output tensor.
dtype	the desired data type of returned tensor. Default: if NULL, infers data type from x.
device	the desired device of returned tensor. Default: if NULL, uses the current device for the default tensor type (see tch_set_default_tensor_type()). device will be the CPU for CPU tensor types and the current CUDA device for CUDA tensor types.
requires_grad	If autograd should record operations on the returned tensor. Default: FALSE.
the	desired layout of returned Tensor. Default: 'strided'

Details

The shape of the tensor is defined by the variable argument sizes.

Examples

tch_randn(c(2,2))
#> tensor 
#> -1.3646  0.7239
#> -0.1713  0.5700
#> [ Variable[CPUFloatType]{2,2} ]
tch_randn(c(2,2), dtype = "double")
#> tensor 
#> -0.4831  1.3880
#>  1.1428  0.0722
#> [ Variable[CPUDoubleType]{2,2} ]