Have a question? Connect with the community at the TensorFlow Forum Visit Forum


Hyperbolic tangent activation function.

For example:

a = tf.constant([-3.0,-1.0, 0.0,1.0,3.0], dtype = tf.float32)
b = tf.keras.activations.tanh(a)
array([-0.9950547, -0.7615942,  0.,  0.7615942,  0.9950547], dtype=float32)

x Input tensor.

Tensor of same shape and dtype of input x, with tanh activation: tanh(x) = sinh(x)/cosh(x) = ((exp(x) - exp(-x))/(exp(x) + exp(-x))).