DEV Community

Super Kai (Kazuya Ito)
Super Kai (Kazuya Ito)

Posted on • Edited on

abs and sqrt in PyTorch

Buy Me a Coffee

*Memos:

abs() can get the 0D or more D tensor of zero or more absolute values from the 0D or more D tensor of zero or more elements as shown below:

*Memos:

  • abs() can be used with torch or a tensor.
  • The 1st argument(input) with torch or using a tensor(Required-Type:tensor of int, float or complex). *If the type is complex, float is returned.
  • There is out argument with torch(Optional-Default:None-Type:tensor): *Memos:
    • out= must be used.
    • My post explains out argument.
  • absolute() is the alias of abs().
import torch

my_tensor = torch.tensor(7)

torch.abs(input=my_tensor)
my_tensor.abs()
# tensor(7)

my_tensor = torch.tensor([7, -1, 5, -7, -9, -3, 0, 6])

torch.abs(input=my_tensor)
# tensor([7, 1, 5, 7, 9, 3, 0, 6])

my_tensor = torch.tensor([[-7, 1, -5, 7],
                          [9, -3, 0, -6]])
torch.abs(input=my_tensor)
# tensor([[7, 1, 5, 7],
#         [9, 3, 0, 6]])

my_tensor = torch.tensor([[7, -1, 5, -7],
                          [-9, -3, 0, 6]])
torch.abs(input=my_tensor)
# tensor([[[7, 1], [5, 7]],
#         [[9, 3], [0, 6]]])

my_tensor = torch.tensor([[[7., -1.], [5., -7.]],
                          [[-9., -3.], [0., 6.]]])
torch.abs(input=my_tensor)
# tensor([[[7., 1.], [5., 7.]],
#         [[9., 3.], [0., 6.]]])

my_tensor = torch.tensor([[[7.+0.j, -1.+0.j], [5.+0.j, -7.+0.j]],
                          [[-9.+0.j, -3.+0.j], [0.+0.j, 6.+0.j]]])
torch.abs(input=my_tensor)
# tensor([[[7., 1.], [5., 7.]],
#         [[9., 3.], [0., 6.]]])
Enter fullscreen mode Exit fullscreen mode

sqrt() can get the 0D or more D tensor of zero or more square roots from the 0D or more D tensor of zero or more elements as shown below:

*Memos:

  • sqrt() can be used with torch or a tensor.
  • The 1st argument(input) with torch or using a tensor(Required-Type:tensor of int, float, complex or bool).
  • There is out argument with torch(Optional-Default:None-Type:tensor): *Memos:
    • out= must be used.
    • My post explains out argument.
import torch

my_tensor = torch.tensor(7)

torch.sqrt(input=my_tensor)
my_tensor.sqrt()
# tensor(2.6458)

my_tensor = torch.tensor([7, -1, 5, -7, -9, -3, 0, 6])

torch.sqrt(input=my_tensor)
# tensor([2.6458, nan, 2.2361, nan, nan, nan, 0.0000, 2.4495])

my_tensor = torch.tensor([[7, -1, 5, -7],
                          [-9, -3, 0, 6]])
torch.sqrt(input=my_tensor)
# tensor([[2.6458, nan, 2.2361, nan],
#         [nan, nan, 0.0000, 2.4495]])

my_tensor = torch.tensor([[[7, -1],
                           [5, -7]],
                          [[-9, -3],
                           [0, 6]]])
torch.sqrt(input=my_tensor)
# tensor([[[2.6458, nan],
#          [2.2361, nan]],
#         [[nan, nan],
#          [0.0000, 2.4495]]])

my_tensor = torch.tensor([[[7., -1.],
                           [5., -7.]],
                          [[-9., -3.],
                           [0., 6.]]])
torch.sqrt(input=my_tensor)
# tensor([[[2.6458, nan],
#          [2.2361, nan]],
#         [[nan, nan],
#          [0.0000, 2.4495]]])

my_tensor = torch.tensor([[[7.+0.j, -1.+0.j],
                           [5.+0.j, -7.+0.j]],
                          [[-9.+0.j, -3.+0.j],
                           [0.+0.j, 6.+0.j]]])
torch.sqrt(input=my_tensor)
# tensor([[[2.6458+0.0000j, 0.0000+1.0000j],
#          [2.2361+0.0000j, 0.0000+2.6458j]],
#         [[0.0000+3.0000j, 0.0000+1.7321j],
#          [0.0000+0.0000j, 2.4495+0.0000j]]])

my_tensor = torch.tensor([[[True, False],
                           [True, False]],
                          [[False, True],
                           [False, True]]])
torch.sqrt(input=my_tensor)
# tensor([[[1., 0.],
#          [1., 0.]],
#         [[0., 1.],
#          [0., 1.]]])
Enter fullscreen mode Exit fullscreen mode

Sentry image

Hands-on debugging session: instrument, monitor, and fix

Join Lazar for a hands-on session where you’ll build it, break it, debug it, and fix it. You’ll set up Sentry, track errors, use Session Replay and Tracing, and leverage some good ol’ AI to find and fix issues fast.

RSVP here →

Top comments (0)

Billboard image

The Next Generation Developer Platform

Coherence is the first Platform-as-a-Service you can control. Unlike "black-box" platforms that are opinionated about the infra you can deploy, Coherence is powered by CNC, the open-source IaC framework, which offers limitless customization.

Learn more

👋 Kindness is contagious

Please leave a ❤️ or a friendly comment on this post if you found it helpful!

Okay