zeros and zeros_like in PyTorch

Buy Me a Coffee☕

*My post explains ones() and ones_like().

zeros() can create the 1D or more D tensor of zero or more 0., 0, 0.+0.j or False as shown below:

*Memos:

• zeros() can be used with torch but not with a tensor.
• The 1st or more arguments with torch are size(Required-Type:int, tuple of int, list of int or size()).
• There is dtype argument with torch(Optional-Default:None-Type:dtype): *Memos:
  • If it's None, get_default_dtype() is used. *My post explains get_default_dtype() and set_default_dtype().
  • dtype= must be used.
  • My post explains dtype argument.
• There is device argument with torch(Optional-Default:None-Type:str, int or device()): *Memos:
  • If it's None, get_default_device() is used. *My post explains get_default_device() and set_default_device().
  • device= must be used.
  • My post explains device argument.
• There is requires_grad argument with torch(Optional-Default:False-Type:bool): *Memos:
  • requires_grad= must be used.
  • My post explains requires_grad argument.
• There is out argument with torch(Optional-Default:None-Type:tensor): *Memos:
  • out= must be used.
  • My post explains out argument.

import torch

torch.zeros(size=())
torch.zeros(size=torch.tensor(8).size())
# tensor(0.)

torch.zeros(size=(0,))
torch.zeros(0)
torch.zeros(size=torch.tensor([]).size())
# tensor([])

torch.zeros(size=(3,))
torch.zeros(3)
torch.zeros(size=torch.tensor([8, 3, 6]).size())
# tensor([0., 0., 0.])

torch.zeros(size=(3, 2))
torch.zeros(3, 2)
torch.zeros(size=torch.tensor([[8, 3], [6, 0], [2, 9]]).size())
# tensor([[0., 0.], [0., 0.], [0., 0.]])

torch.zeros(size=(3, 2, 4))
torch.zeros(3, 2, 4)
# tensor([[[0., 0., 0., 0.], [0., 0., 0., 0.]],
#         [[0., 0., 0., 0.], [0., 0., 0., 0.]],
#         [[0., 0., 0., 0.], [0., 0., 0., 0.]]])

torch.zeros(size=(3, 2, 4), dtype=torch.int64)
torch.zeros(3, 2, 4, dtype=torch.int64)
# tensor([[[0, 0, 0, 0], [0, 0, 0, 0]],
#         [[0, 0, 0, 0], [0, 0, 0, 0]],
#         [[0, 0, 0, 0], [0, 0, 0, 0]]])

torch.zeros(size=(3, 2, 4), dtype=torch.complex64)
torch.zeros(3, 2, 4, dtype=torch.complex64)
# tensor([[[0.+0.j, 0.+0.j, 0.+0.j, 0.+0.j],
#          [0.+0.j, 0.+0.j, 0.+0.j, 0.+0.j]],
#         [[0.+0.j, 0.+0.j, 0.+0.j, 0.+0.j],
#          [0.+0.j, 0.+0.j, 0.+0.j, 0.+0.j]],
#         [[0.+0.j, 0.+0.j, 0.+0.j, 0.+0.j],
#          [0.+0.j, 0.+0.j, 0.+0.j, 0.+0.j]]])

torch.zeros(size=(3, 2, 4), dtype=torch.bool)
torch.zeros(3, 2, 4, dtype=torch.bool)
# tensor([[[False, False, False, False],
#          [False, False, False, False]],
#         [[False, False, False, False],
#          [False, False, False, False]],
#         [[False, False, False, False],
#          [False, False, False, False]]])

zeros_like() can replace the zero or more floating-point numbers, integers, complex numbers or boolean values of a 0D or more D tensor with zero or more 0., 0, 0.+0.j or False as shown below:

*Memos:

• zeros_like() can be used with torch but not with a tensor.
• The 1st argument with torch is input(Required-Type:tensor of int, float, complex or bool).
• There is dtype argument with torch(Optional-Default:None-Type:dtype): *Memos:
  • If it's None, it's inferred from input.
  • dtype= must be used.
  • My post explains dtype argument.
• There is device argument with torch(Optional-Default:None-Type:str, int or device()): *Memos:
  • If it's None, it's inferred from input.
  • device= must be used.
  • My post explains device argument.
• There is requires_grad argument with torch(Optional-Default:False-Type:bool): *Memos:
  • requires_grad= must be used.
  • My post explains requires_grad argument.

import torch

my_tensor = torch.tensor(7.)

torch.zeros_like(input=my_tensor)
# tensor(0.)

my_tensor = torch.tensor([7., 4., 5.])

torch.zeros_like(input=my_tensor)
# tensor([0., 0., 0.])

my_tensor = torch.tensor([[7., 4., 5.], [2., 8., 3.]])

torch.zeros_like(input=my_tensor)
# tensor([[0., 0., 0.], [0., 0., 0.]])

my_tensor = torch.tensor([[[7., 4., 5.], [2., 8., 3.]],
                          [[6., 0., 1.], [5., 9., 4.]]])
torch.zeros_like(input=my_tensor)
# tensor([[[0., 0., 0.], [0., 0., 0.]],
#         [[0., 0., 0.], [0., 0., 0.]]])

my_tensor = torch.tensor([[[7, 4, 5], [2, 8, 3]],
                          [[6, 0, 1], [5, 9, 4]]])
torch.zeros_like(input=my_tensor)
# tensor([[[0, 0, 0], [0, 0, 0]],
#         [[0, 0, 0], [0, 0, 0]]])

my_tensor = torch.tensor([[[7.+4.j, 4.+2.j, 5.+3.j],
                           [2.+5.j, 8.+1.j, 3.+9.j]],
                          [[6.+9.j, 0.+3.j, 1.+8.j],
                           [5.+3.j, 9.+4.j, 4.+6.j]]])
torch.zeros_like(input=my_tensor)
# tensor([[[0.+0.j, 0.+0.j, 0.+0.j],
#          [0.+0.j, 0.+0.j, 0.+0.j]],
#         [[0.+0.j, 0.+0.j, 0.+0.j],
#          [0.+0.j, 0.+0.j, 0.+0.j]]])

my_tensor = torch.tensor([[[True, False, True], [False, True, False]], 
                          [[False, True, False], [True, False, True]]])
torch.zeros_like(input=my_tensor)
# tensor([[[False, False, False], [False, False, False]],
#         [[False, False, False], [False, False, False]]])