leaky_relu¶

dragon.vm.torch.nn.functional.leaky_relu(
  input,
  negative_slope=0.01,
  inplace=False
)[source]¶

Apply the leaky rectified linear unit to input.

The LeakyReLU function is defined as:

\[\text{LeakyReLU}(x) = \begin{cases} x, & \text{ if } x \geq 0 \\ slope * x, & \text{ otherwise } \end{cases} \]

Parameters:

• input (dragon.vm.torch.Tensor) – The input tensor.
• negative_slope (float, optional, default=0.01) – The slope to the negative side.
• inplace (bool, optional, default=False) – Whether to do the operation in-place.

Returns:

dragon.vm.torch.Tensor – The output tensor.

See also

torch.nn.LeakyReLU(…)