MLP_Python

Contains a Multi-Layer Perceptron (MLP) implementation using PyTorch and the train_nn function to train the network.

MLP

Bases: Module

              flowchart TD
              mmm_audio.MLP_Python.MLP[MLP]

              

              click mmm_audio.MLP_Python.MLP href "" "mmm_audio.MLP_Python.MLP"
            

The Multi-Layer Perceptron (MLP) class.

__init__(input_size, layers_data)

Initialize the MLP.

Parameters:

Name	Type	Description	Default
input_size	int	Size of the input layer.	required
layers_data	list	A list of tuples where each tuple contains the size of the layer and the activation function.	required

forward(input_data)

Forward pass through the MLP.

Parameters:

Name	Type	Description	Default
input_data	list[list[float]]	Input tensor.	required

get_input_size()

Get the input size of the MLP.

get_output_size()

Get the output size of the MLP.

train_nn(X_train_list, y_train_list, layers, learn_rate, epochs, file_name)

Train the MLP and save the trained model.

Parameters:

Name	Type	Description	Default
X_train_list	list[list[float]]	List of input training data.	required
y_train_list	list[list[float]]	List of output training data.	required
layers	list[tuple[int, str | None]]	List of layer specifications (size and activation).	required
learn_rate	float	Learning rate for the optimizer.	required
epochs	int	Number of training epochs.	required
file_name	str	File name to save the trained model.	required