public class
Sigmoid
Sigmoid activation. sigmoid(x) = 1 / (1 + exp(-x)).
Applies the sigmoid activation function. For small values (<-5), sigmoid
returns a value close to zero, and for large values (>5) the result of the function gets close
to 1.
Sigmoid is equivalent to a 2-element Softmax, where the second element is assumed to be zero. The sigmoid function always returns a value between 0 and 1.
For example:
Operand<TFloat32> input = tf.constant(
new float[] {-20f, -1.0f, 0.0f, 1.0f, 20f});
Sigmoid<TFloat32> sigmoid = new Sigmoid<>(tf);
Operand<TFloat32> result = sigmoid.call(input);
// result is [2.0611537e-09f, 2.6894143e-01f,
// 5.0000000e-01f,7.3105860e-01f, 1.f]
Public Constructors
|
Sigmoid(Ops tf)
Creates a Sigmoid activation.
|
Public Methods
| Operand<T> |
Inherited Methods
Public Constructors
public Sigmoid (Ops tf)
Creates a Sigmoid activation.
Parameters
| tf | the TensorFlow Ops |
|---|