phitodeep.model

Classes

Sequential
SequentialBuilder	Fluent API for building Sequential models.

Module Contents

class phitodeep.model.Sequential(*layers, alpha=0.01, optimizer: phitodeep.optimization.optimizers.Optimizer = o.Adam(), batch_size=None, epochs=1000, loss_class=ls.MeanSquaredError())

layers = []

alpha = 0.01

optimizer_type

batch_size = None

epochs = 1000

loss_class

add(layer) → None

Add a layer to the network.

setoptimizer(optimizer)

setbatchsize(num)

setloss(loss_class)

train(X, y, X_test, y_test)

Train the model using the specified optimizer and loss function.

Parameters:

• X (np.ndarray) – Training data.

• y (np.ndarray) – Training labels.

• X_test (np.ndarray) – Test data.

• y_test (np.ndarray) – Test labels.

Returns:

A list of tuples containing the training and test losses for each epoch.

Return type:

list

predict(X)

Forward pass through all layers.

Parameters:

X – input array

Returns:

output after passing through all layers

backward(gradient)

Backward pass through all layers.

Parameters:

gradient – dL/dY from loss function (shape: batch_size x output_size)

Propagates gradient backwards through all layers in reverse order. Each layer computes its parameter gradients, updates parameters, and returns the gradient for the previous layer.

__call__(X)

Allow model(X) syntax.

summary()

Print model architecture.

copy()

Return a copy of the model.

class phitodeep.model.SequentialBuilder

Fluent API for building Sequential models.

layers = []

alpha_value = 1

optimizer_type

batch_size = None

epochs_value = 1000

loss_class

flatten()

Add a Flatten layer.

dense(input_size, output_size, initializer=He())

Add a Dense layer.

relu()

Add a ReLU activation.

sigmoid()

Add a Sigmoid activation.

tanh()

Add a Tanh activation.

softmax()

Add a Softmax activation.

elu(alpha_activation=1.0)

Add an ELU activation.

optimizer(optimizer)

Set the optimizer.

batch(num)

Set the batch size.

alpha(num)

Set the learning rate.

epochs(num)

Set the number of epochs.

loss(loss_class)

Set the loss function.

build()

Build and return the Sequential model.