relu

dragon.vm.tensorflow.keras.activations.relu(
  x,
  alpha=0,
  max_value=None,
  **kwargs
)[source]

Apply the rectified linear unit to input. [Nair & Hinton, 2010].

The ReLU function is defined as:

\[\text{ReLU}(x) = \begin{cases} \min(x, v_{max}), & \text{ if } x \geq 0 \\ \alpha * x, & \text{ otherwise } \end{cases} \]

Examples:

x = tf.constant([-1, 0, 1], 'float32')
print(tf.keras.activations.relu(x, inplace=False))
Parameters:
  • x (dragon.Tensor) – The input tensor.
  • alpha (number, optional, default=0) – The valve of \(\alpha\).
  • max_value (number, optional) – The value of \(v_{max}\).