Mish class

The Mish activation function.

Mish is a modern, self-gated, and smooth non-monotonic activation function that has achieved state-of-the-art results on a number of computer vision and NLP benchmarks, often outperforming ReLU and Swish.

The function is defined as $f(x) = x \cdot \tanh(\text{softplus}(x))$.

Example

Layer hiddenLayer = DenseLayer(128, activation: Mish());

Implemented types

• ActivationFunction

Constructors

Mish()

Properties

hashCode → int

The hash code for this object.

no setter, inherited

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

call(Tensor input) → Tensor<Vector>

Applies the Mish function element-wise to the input tensor.

override

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited