mfcc_cnn.py

import numpy as np
import tensorflow.keras as keras

def build_model(input_shape):
    """Generates CNN model
    :param input_shape (tuple): Shape of input set
    :return model: CNN model
    """

    # build network topology
    model = keras.Sequential()

    # 1st conv layer
    model.add(keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=input_shape))
    model.add(keras.layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same'))
    model.add(keras.layers.BatchNormalization())

    # 2nd conv layer
    model.add(keras.layers.Conv2D(32, (3, 3), activation='relu'))
    model.add(keras.layers.MaxPooling2D((3, 3), strides=(2, 2), padding='same'))
    model.add(keras.layers.BatchNormalization())

    # 3rd conv layer
    model.add(keras.layers.Conv2D(32, (2, 2), activation='relu'))
    model.add(keras.layers.MaxPooling2D((2, 2), strides=(2, 2), padding='same'))
    model.add(keras.layers.BatchNormalization())

    # flatten output and feed it into dense layer
    model.add(keras.layers.Flatten())
    model.add(keras.layers.Dense(64, activation='relu'))
    model.add(keras.layers.Dropout(0.3))

    # output layer
    model.add(keras.layers.Dense(2, activation='softmax'))
    
    optimiser = keras.optimizers.Adam(learning_rate=0.0001)
    model.compile(optimizer=optimiser,
                  loss='sparse_categorical_crossentropy',
                  metrics=['accuracy'])

    model.summary()

    return model
  
  # input_shape = (X_train.shape[1], X_train.shape[2]) # 130, 13
  # model = build_model(input_shape)
  # history = model.fit(X_train, y_train, validation_data=(X_validation, y_validation), batch_size=32, epochs=30)