TensorFlow 1 version
|
Built-in activation functions.
Functions
deserialize(...): Returns activation function given a string identifier.
elu(...): Exponential Linear Unit.
exponential(...): Exponential activation function.
get(...): Returns function.
hard_sigmoid(...): Hard sigmoid activation function.
linear(...): Linear activation function (pass-through).
relu(...): Applies the rectified linear unit activation function.
selu(...): Scaled Exponential Linear Unit (SELU).
serialize(...): Returns the string identifier of an activation function.
sigmoid(...): Sigmoid activation function, sigmoid(x) = 1 / (1 + exp(-x)).
softmax(...): Softmax converts a real vector to a vector of categorical probabilities.
softplus(...): Softplus activation function, softplus(x) = log(exp(x) + 1).
softsign(...): Softsign activation function, softsign(x) = x / (abs(x) + 1).
swish(...): Swish activation function, swish(x) = x * sigmoid(x).
tanh(...): Hyperbolic tangent activation function.