Class Softsign

java.lang.Object
org.tensorflow.framework.activations.AbstractActivation
org.tensorflow.framework.activations.Softsign
All Implemented Interfaces:
Activation
public class Softsign extends AbstractActivation
Softsign activation function, softsign(x) = x / (abs(x) + 1).

Example Usage: 

Operand<TFloat32> input = tf.constant(
         new float[] {-1.0f, 0.0f, 1.0f});
Softsign<TFloat32> softsign = new Softsign<>(tf);
Operand<TFloat32> result = softsign.call(input);
// result is [-0.5f, 0.f, 0.5f]

  • Field Details

  • Constructor Details

    • Softsign

      public Softsign()
      Creates a Softsign activation.

    • Softsign

      public Softsign(Map<String,Object> config)
      Creates a new Softsign from a configuration Map
      Parameters:
      config - the configuration map, this class does not use any of the entries in the configuration map
      Throws:
      IllegalArgumentException - if the configuration contains unsupported keys for this class or if the value for the name key does not match the name for the Activation

  • Method Details

    • softsign

      public static <T extends TNumber> Operand<T> softsign(Ops tf, Operand<T> input)
      Applies the Softsign activation function, softsign(x) = x / (abs(x) + 1).

      Example Usage: 

      Operand<TFloat32> input = ...;
Operand<TFloat32> result = Softsign.softsign(tf, input);
      Type Parameters:
      T - the data type for the input
      Parameters:
      tf - the TensorFlow Ops
      input - the input
      Returns:
      the Softsign activation, softsign(x) = x / (abs(x) + 1).

    • call

      public <T extends TNumber> Operand<T> call(Ops tf, Operand<T> input)
      Gets the calculation operation for the activation.
      Type Parameters:
      T - the data type of the input and the result
      Parameters:
      tf - the TensorFlow Ops
      input - the input tensor
      Returns:
      The operand for the activation

    • getConfig

      public Map<String,Object> getConfig()
      Gets a configuration map
      Specified by:
      getConfig in class AbstractActivation
      Returns:
      the configuration map

    • getName

      public String getName()
      Get the name of the activation as known by the TensorFlow Engine
      Specified by:
      getName in class AbstractActivation
      Returns:
      the name of the activation as known by the TensorFlow Engine