empty(), empty_like() and empty_strided in PyTorch

empty() can create a 1D or more D tensor filled with the zero or more numbers in memory which is called uninitialized data.

*Memos:

• You can use torch.Tensor() or torch.FloatTensor() like torch.Tensor(3, 2, 4) or torch.FloatTensor(3, 2, 4) because they can do the same job as empty(). *torch.Tensor() is the alias of torch.FloatTensor() by default.


• 
  empty() can be used only from torch but not from a tensor
  

import torch

torch.empty(0)
torch.empty((0,))
# tensor([])

torch.empty(3)
torch.empty((3,))
# tensor([-1.3610e+13, 4.4916e-41, -1.3610e+13]) …

data empty job memory memos numbers pytorch tensor torch