Layers¶

Layers are the building blocks of a Neural Network. They are the individual neurons that are connected to each other to form the network. Each layer has a specific number of neurons and an activation function.

class NeuralNetPy.layers.Dense¶

Bases: Layer

Initializes a Dense layer, which is the backbone of a Neural Network.

Parameters:

nNeurons (int) – The number of neurons in the layer
activationFunc (ACTIVATION) – The activation function to be used, defaults to SIGMOID
weightInit (WEIGHT_INIT) – The weight initialization method to be used, defaults to RANDOM
bias (int) – The bias to be used, defaults to 0

Example¶

    import NeuralNetPy as NNP

    layer = NNP.layers.Dense(3, NNP.ACTIVATION.RELU, NNP.WEIGHT_INIT.HE)

typeStr(self: NeuralNetPy.layers.Dense) → str¶: Returns the type of the layer.

class NeuralNetPy.layers.Dropout¶

Bases: Layer

Initializes a Dropout layer, it’s a layer that simply applies a dropout to the input.

Parameters:

rate (float32) – A float between 0 and 1. It represents the fraction of the inputs to drop.
seed (int) – An integer used as random seed. If not provided a random seed will be generated.

typeStr(self: NeuralNetPy.layers.Dropout) → str¶: Returns the type of the layer.

class NeuralNetPy.layers.Flatten¶

Bases: Layer

Initializes a Flatten layer. The sole purpose of this layer is to vectorize matrix inputs like images.

Parameters:: inputShape (tuple) – The shape of the input matrix (rows, cols or number of pixels per row and column in the case of images)

Example¶

    import NeuralNetPy as NNP

    layer = NNP.layers.Flatten((3, 3))

typeStr(self: NeuralNetPy.layers.Flatten) → str¶: Returns the type of the layer.