Empty
torch_empty( ..., names = NULL, dtype = NULL, layout = torch_strided(), device = NULL, requires_grad = FALSE )
... | a sequence of integers defining the shape of the output tensor. |
---|---|
names | optional character vector naming each dimension. |
dtype | ( |
layout | ( |
device | ( |
requires_grad | (bool, optional) If autograd should record operations on the returned tensor. Default: |
Returns a tensor filled with uninitialized data. The shape of the tensor is
defined by the variable argument size
.
#> torch_tensor #> 4.4726e+21 8.4843e+26 2.7945e+20 #> 5.5610e+31 4.2964e+24 8.4725e+11 #> [ CPUFloatType{2,3} ]