Here we are back with another interesting Keras tutorial which will teach you about Keras Custom Layers.

A Neural Network is a stack of layers. Each layer receives some input, makes computation on this input and propagates the output to the next layer. Though there are many in-built layers in Keras for different use cases, Keras Layers like Conv2D, MaxPooling2D, Dense, Flatten have different applications and we use them according to our requirements. But sometimes we may want to perform computations other than what these Keras Layers do.

Therefore we have to build our own layer and define our own algorithm for computation on input data. Keras provides this feature to write our own Custom Layers. In this article we will study the concept of Custom Layers and we will see some examples to build our own custom layer.

#keras #lambda