TensorFlow 1 version | View source on GitHub |
Sigmoid activation function.
tf.keras.activations.sigmoid(
x
)
Applies the sigmoid activation function. The sigmoid function is defined as 1 divided by (1 + exp(-x)). It's curve is like an "S" and is like a smoothed version of the Heaviside (Unit Step Function) function. For small values (<-5) the sigmoid returns a value close to zero and for larger 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.
For example:
a = tf.constant([-20, -1.0, 0.0, 1.0, 20], dtype = tf.float32)
b = tf.keras.activations.sigmoid(a)
b.numpy() >= 0.0
array([ True, True, True, True, True])
Arguments | |
---|---|
x
|
Input tensor. |
Returns | |
---|---|
Tensor with the sigmoid activation: (1.0 / (1.0 + exp(-x))) .
Tensor will be of same shape and dtype of input x .
|