DEV Community

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

Posted on

sub in PyTorch

Buy Me a Coffee

*Memos:

sub() can do subtraction with two of the 0D or more D tensors of zero or more elements or scalars or the 0D or more D tensor of zero or more elements and a scalar, getting the 0D or more D tensor of zero or more elements as shown below:

*Memos:

  • sub() can be used with torch or a tensor.
  • The 1st argument(input) with torch(Type:tensor or scalar of int, float or complex) or using a tensor(Type:tensor of int, float or complex)(Required).
  • The 2nd argument with torch or the 1st argument with a tensor is other(Required-Type:tensor or scalar of int, float or complex).
  • The 3rd argument with torch or the 2nd argument with a tensor is alpha(Optional-Default:1-Type:tensor or scalar of int, float or complex). *otheris multiplied by alpha(input or a tensor-(otherxalpha)).
  • There is out argument with torch(Optional-Default:None-Type:tensor): *Memos:
    • out= must be used.
    • My post explains out argument.
  • subtract() is the alias of sub().
import torch

tensor1 = torch.tensor([9, 7, 6])
tensor2 = torch.tensor([[4, -4, 3], [-2, 5, -5]])

torch.sub(input=tensor1, other=tensor2)
tensor1.sub(other=tensor2)
torch.sub(input=tensor1, other=tensor2, alpha=1)
torch.sub(input=tensor1, other=tensor2, alpha=torch.tensor(1))
# tensor([[5, 11, 3], [11, 2, 11]])

torch.sub(input=tensor1, other=tensor2, alpha=0)
torch.sub(input=tensor1, other=tensor2, alpha=torch.tensor(0))
# tensor([[9, 7, 6], [9, 7, 6]])

torch.sub(input=tensor1, other=tensor2, alpha=2)
torch.sub(input=tensor1, other=tensor2, alpha=torch.tensor(2))
# tensor([[1, 15, 0], [13, -3, 16]])

torch.sub(input=tensor1, other=tensor2, alpha=-1)
torch.sub(input=tensor1, other=tensor2, alpha=torch.tensor(-1))
# tensor([[13, 3, 9], [7, 12, 1]])

torch.sub(input=tensor1, other=tensor2, alpha=-2)
torch.sub(input=tensor1, other=tensor2, alpha=torch.tensor(-2))
# tensor([[17, -1, 12], [5, 17, -4]])

torch.sub(input=9, other=tensor2)
torch.sub(input=9, other=tensor2, alpha=1)
torch.sub(input=9, other=tensor2, alpha=torch.tensor(1))
# tensor([[5, 13, 6], [11, 4, 14]])

torch.sub(input=tensor1, other=4)
torch.sub(input=tensor1, other=4, alpha=1)
torch.sub(input=tensor1, other=4, alpha=torch.tensor(1))
# tensor([5, 3, 2])

torch.sub(input=9, other=4)
torch.sub(input=9, other=4, alpha=1)
torch.sub(input=9, other=4, alpha=torch.tensor(1))
# tensor(5)

tensor1 = torch.tensor([9., 7., 6.])
tensor2 = torch.tensor([[4., -4., 3.], [-2., 5., -5.]])

torch.sub(input=tensor1, other=tensor2)
torch.sub(input=tensor1, other=tensor2, alpha=1.)
torch.sub(input=tensor1, other=tensor2, alpha=torch.tensor(1.))
# tensor([[5., 11., 3.], [11., 2., 11.]])

torch.sub(input=9., other=tensor2)
torch.sub(input=9., other=tensor2, alpha=1.)
torch.sub(input=9., other=tensor2, alpha=torch.tensor(1.))
# tensor([[5., 13., 6.], [11., 4., 14.]])

torch.sub(input=tensor1, other=4)
torch.sub(input=tensor1, other=4, alpha=1.)
torch.sub(input=tensor1, other=4, alpha=torch.tensor(1.))
# tensor([5., 3., 2.])

torch.sub(input=9., other=4)
torch.sub(input=9., other=4, alpha=1.)
torch.sub(input=9., other=4, alpha=torch.tensor(1.))
# tensor(5.)

tensor1 = torch.tensor([9.+0.j, 7.+0.j, 6.+0.j])
tensor2 = torch.tensor([[4.+0.j, -4.+0.j, 3.+0.j],
                        [-2.+0.j, 5.+0.j, -5.+0.j]])
torch.sub(input=tensor1, other=tensor2)
torch.sub(input=tensor1, other=tensor2, alpha=1.+0.j)
torch.sub(input=tensor1, other=tensor2, alpha=torch.tensor(1.+0.j))
# tensor([[5.+0.j, 11.+0.j, 3.+0.j],
#         [11.+0.j, 2.+0.j, 11.+0.j]])

torch.sub(input=9.+0.j, other=tensor2)
torch.sub(input=9.+0.j, other=tensor2, alpha=1.+0.j)
torch.sub(input=9.+0.j, other=tensor2, alpha=torch.tensor(1.+0.j))
# tensor([[5.+0.j, 13.+0.j, 6.+0.j],
#         [11.+0.j, 4.+0.j, 14.+0.j]])

torch.sub(input=tensor1, other=4.+0.j)
torch.sub(input=tensor1, other=4.+0.j, alpha=1.+0.j)
torch.sub(input=tensor1, other=4.+0.j, alpha=torch.tensor(1.+0.j))
# tensor([5.+0.j, 3.+0.j, 2.+0.j])

torch.sub(input=9.+0.j, other=4.+0.j)
torch.sub(input=9.+0.j, other=4.+0.j, alpha=1.+0.j)
torch.sub(input=9.+0.j, other=4.+0.j, alpha=torch.tensor(1.+0.j))
# tensor(5.+0.j)
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)

A Workflow Copilot. Tailored to You.

Pieces.app image

Our desktop app, with its intelligent copilot, streamlines coding by generating snippets, extracting code from screenshots, and accelerating problem-solving.

Read the docs

👋 Kindness is contagious

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

Okay