leaky_relu

class torch.ao.nn.quantized.functional.leaky_relu(input, negative_slope=0.01, inplace=False, scale=None, zero_point=None)

Quantized version of the. leaky_relu(input, negative_slope=0.01, inplace=False, scale, zero_point) -> Tensor

Applies element-wise, $\text{LeakyReLU}(x) = \max(0, x) + \text{negative\_slope} * \min(0, x)$

参数

• input (Tensor) – Quantized input

• negative_slope (float) – The slope of the negative input

• inplace (bool) – Inplace modification of the input tensor

• scale (Optional[float]) – Scale and zero point of the output tensor.

• zero_point (Optional[int]) – Scale and zero point of the output tensor.

See LeakyReLU for more details.