Shortcuts

torch.heaviside

torch.heaviside(input, values, *, out=None) → Tensor

Computes the Heaviside step function for each element in input. The Heaviside step function is defined as:

heaviside(input,values)={0,if input < 0values,if input == 01,if input > 0\text{{heaviside}}(input, values) = \begin{cases} 0, & \text{if input < 0}\\ values, & \text{if input == 0}\\ 1, & \text{if input > 0} \end{cases}
Parameters
  • input (Tensor) – the input tensor.

  • values (Tensor) – The values to use where input is zero.

Keyword Arguments

out (Tensor, optional) – the output tensor.

Example:

>>> input = torch.tensor([-1.5, 0, 2.0])
>>> values = torch.tensor([0.5])
>>> torch.heaviside(input, values)
tensor([0.0000, 0.5000, 1.0000])
>>> values = torch.tensor([1.2, -2.0, 3.5])
>>> torch.heaviside(input, values)
tensor([0., -2., 1.])

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources