torch.clamp#

torch.clamp(input,min=None,max=None,*,out=None)→Tensor#

Clamps all elements ininput into the range[min,max].Letting min_value and max_value bemin andmax, respectively, this returns:

$$y_i=\min (\max (x_i,{\text{min\_value}}_i),{\text{max\_value}}_i)$$yi​=min(max(xi​,min_valuei​),max_valuei​)

Ifmin isNone, there is no lower bound.Or, ifmax isNone there is no upper bound.

Note

Ifmin is greater thanmaxtorch.clamp(...,min,max)sets all elements ininput to the value ofmax.

Parameters

• input (Tensor) – the input tensor.

• min (Number orTensor,optional) – lower-bound of the range to be clamped to

• max (Number orTensor,optional) – upper-bound of the range to be clamped to

Keyword Arguments

out (Tensor,optional) – the output tensor.

Example:

>>>a=torch.randn(4)>>>atensor([-1.7120,  0.1734, -0.0478, -0.0922])>>>torch.clamp(a,min=-0.5,max=0.5)tensor([-0.5000,  0.1734, -0.0478, -0.0922])>>>min=torch.linspace(-1,1,steps=4)>>>torch.clamp(a,min=min)tensor([-1.0000,  0.1734,  0.3333,  1.0000])