Models

Models are used in machine learning to make predictions or decisions without being explicitly programmed to do so.

class NeuralNetPy.models.Model

Bases: pybind11_object

Base class for all models

static load_from_file(arg0: str, arg1: NeuralNet::Network) → None

This function will load the parameters of a Model from a binary file.

Usage
import NeuralNetPy as NNP

# Initialize an empty network            
network = NNP.models.Network()

# Populate it with previously saved parameters
NNP.models.Model.load_from_file("network.bin", network)
static save_to_file(arg0: str, arg1: NeuralNet::Network) → None

This function will save the given Model’s parameters in a binary file.

Usage
import NeuralNetPy as NNP

network = NNP.models.Network()
network.setup(optimizer=NNP.optimizers.SGD(0.01))
network.addLayer(NNP.layers.Dense(3, NNP.ACTIVATION.RELU, NNP.WEIGHT_INIT.HE))
network.addLayer(NNP.layers.Dense(2, NNP.ACTIVATION.SIGMOID, NNP.WEIGHT_INIT.HE))

# ... after training

NNP.models.Model.save_to_file(network, "network.bin")

Warning

The file content will be overwritten if it already exists.

class NeuralNetPy.models.Network

Bases: Model

This is the base of a Neural Network. You can setup the network with the given optimizer and loss function.

Parameters:

  • optimizer (Optimizer) – The optimizer to be used from the optimizers module

  • loss (LOSS) – The loss function to be used from the LOSS enum, defaults to QUADRATIC

Example
import NeuralNetPy as NNP

network = NNP.models.Network()
network.setup(optimizer=NNP.SGD(0.01), loss=NNP.LOSS.MCQ)
addLayer(self: NeuralNetPy.models.Network, arg0: NeuralNetPy.layers.Layer) → None

Add a layer to the network.

Parameters:

layer (Layer) – The layer to be added

Example
import NeuralNetPy as NNP

network = NNP.models.Network()
network.addLayer(NNP.layers.Dense(3, NNP.ACTIVATION.RELU, NNP.WEIGHT_INIT.HE))

Warning

The order of the layers added is important, it will reflect the overall structure of the network.

Danger

Under no circumstances you should add a Flatten layer as a hidden layer.

getLayer(self: NeuralNetPy.models.Network, arg0: int) → NeuralNetPy.layers.Layer

Get a layer from the network by it’s index. They’re 0-indexed.

Parameters:

index (int) – The index of the layer

Returns:

The layer at the given index

Return type:

Layer

Example
import NeuralNetPy as NNP

network = NNP.models.Network()
network.addLayer(NNP.layers.Dense(3, NNP.ACTIVATION.RELU, NNP.WEIGHT_INIT.HE))
network.addLayer(NNP.layers.Dense(2, NNP.ACTIVATION.SIGMOID, NNP.WEIGHT_INIT.HE))

layer = network.getLayer(1) # Return Dense layer with 2 neurons
getNumLayers(self: NeuralNetPy.models.Network) → int

Return the number of layers in the network.

getSlug(self: NeuralNetPy.models.Network) → str
predict(*args, **kwargs)

Overloaded function.

  1. predict(self: NeuralNetPy.models.Network, arg0: List[List[float]]) -> numpy.ndarray[numpy.float64[m, n]]

    Feed forward the given inputs through the network and return the predictions/outputs.

    param inputs:

    A list of vectors representing the inputs

    type inputs:

    list[list[float]]

    return:

    A matrix representing the outputs of the network for the given inputs

    rtype:

    numpy.ndarray

  2. predict(self: NeuralNetPy.models.Network, arg0: List[List[List[float]]]) -> numpy.ndarray[numpy.float64[m, n]]

    Feed forward the given inputs through the network and return the predictions/outputs.

    param inputs:

    A list of vectors representing the inputs

    type inputs:

    list[list[list[float]]]

    return:

    A matrix representing the outputs of the network for the given inputs

    rtype:

    numpy.ndarray

setup(self: NeuralNetPy.models.Network, optimizer: NeuralNetPy.optimizers.Optimizer, loss: NeuralNetPy.LOSS = <LOSS.QUADRATIC: 1>) → None
train(*args, **kwargs)

Overloaded function.

  1. train(self: NeuralNetPy.models.Network, inputs: List[List[float]], targets: List[float], epochs: int, callbacks: List[NeuralNetPy.callbacks.Callback] = [], progBar: bool = True) -> float

    Train the network by passing it 2 dimensional inputs (vectors).

    param inputs:

    A list of vectors representing the inputs

    type inputs:

    list[list[float]]

    param labels:

    A list of labels

    type labels:

    list[float]

    param epochs:

    The number of epochs to train the network

    type epochs:

    int

    param callbacks:

    A list of callbacks to be used during the training

    type callbacks:

    list[Callback]

    param progBar:

    Whether or not to enable the progress bar

    type progBar:

    bool

    return:

    The average loss throughout the training

    rtype:

    float

    Example
    import NeuralNetPy as NNP

network = NNP.models.Network()
network.setup(optimizer=NNP.optimizers.SGD(0.01), loss=NNP.LOSS.MCQ)
network.addLayer(NNP.layers.Dense(3, NNP.ACTIVATION.RELU, NNP.WEIGHT_INIT.HE))
network.addLayer(NNP.layers.Dense(2, NNP.ACTIVATION.SIGMOID, NNP.WEIGHT_INIT.HE))

inputs = [
  [0.4, 0.5, 0.67],
  [0.3, 0.2, 0.1],
  [0.1, 0.2, 0.3]
]

labels = [1, 0, 1]

loss = network.train(inputs, labels, 10)

  2. train(self: NeuralNetPy.models.Network, inputs: List[List[List[float]]], targets: List[float], epochs: int, callbacks: List[NeuralNetPy.callbacks.Callback] = [], progBar: bool = True) -> float

    Train the network by passing it a list of 3 dimensional inputs (matrices).

    param inputs:

    A list of matrices representing the inputs

    type inputs:

    list[list[list[float]]]

    param labels:

    A list of labels

    type labels:

    list[float]

    param epochs:

    The number of epochs to train the network

    type epochs:

    int

    param callbacks:

    A list of callbacks to be used during the training

    type callbacks:

    list[Callback]

    param progBar:

    Whether or not to enable the progress bar

    type progBar:

    bool

    return:

    The average loss throughout the training

    rtype:

    float

  3. train(self: NeuralNetPy.models.Network, trainingData: NeuralNetPy.TrainingData2dI, epochs: int, callbacks: List[NeuralNetPy.callbacks.Callback] = [], progBar: bool = True) -> float

    Train the network by passing it a TrainingData2dI object.

    param trainingData:

    A TrainingData2dI object

    type trainingData:

    TrainingData2dI

    param epochs:

    The number of epochs to train the network

    type epochs:

    int

    param callbacks:

    A list of callbacks to be used during the training

    type callbacks:

    list[Callback]

    param progBar:

    Whether or not to enable the progress bar

    type progBar:

    bool

    return:

    The average loss throughout the training

    rtype:

    float

  4. train(self: NeuralNetPy.models.Network, trainingData: NeuralNetPy.TrainingData3dI, epochs: int, callbacks: List[NeuralNetPy.callbacks.Callback] = [], progBar: bool = True) -> float

    Train the network by passing it a TrainingData3dI object.

    param trainingData:

    A TrainingData3dI object

    type trainingData:

    TrainingData3dI

    param epochs:

    The number of epochs to train the network

    type epochs:

    int

    param callbacks:

    A list of callbacks to be used during the training

    type callbacks:

    list[Callback]

    param progBar:

    Whether or not to enable the progress bar

    type progBar:

    bool

    return:

    The average loss throughout the training

    rtype:

    float