Hardtanh

class torch.nn.modules.activation.Hardtanh(min_val=-1.0, max_val=1.0, inplace=False, min_value=None, max_value=None)

Applies the HardTanh function element-wise.

HardTanh is defined as:

$$\text{HardTanh}(x)=\{\begin{array}{ll}\text{max\_val}& \text{ if }x>\text{ max\_val }\\ \text{min\_val}& \text{ if }x<\text{ min\_val }\\ x& \text{ otherwise }\end{array}$$

Parameters

• min_val (float) – minimum value of the linear region range. Default: -1

• max_val (float) – maximum value of the linear region range. Default: 1

• inplace (bool) – can optionally do the operation in-place. Default: False

Keyword arguments min_value and max_value have been deprecated in favor of min_val and max_val.

Shape:

• Input: $(\ast )$, where $\ast$ means any number of dimensions.

• Output: $(\ast )$, same shape as the input.

Examples:

>>> m = nn.Hardtanh(-2, 2)
>>> input = torch.randn(2)
>>> output = m(input)

extra_repr()

Return the extra representation of the module.

Return type

str

forward(input)

Runs the forward pass.

Return type

Tensor