A swish activation layer applies the swish function on the layer inputs.The swish operation is given by $$f(x)=\frac{x}{1+e^{-x}}$$. The swish layer does not change the size of its input.

Activation layers such as swish layers improve the training accuracy for some applications and usually follow convolution and normalization layers. Other nonlinear activation layers perform different operations. For a list of activation layers, seeActivation Layers.