alex_net.py

def alex_net(shape):
    from keras.models import Model
    from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten, Input, BatchNormalization, Dropout
    from keras.regularizers import l2

    weight_decay = 1e-4
    inputs = Input(shape=shape)

    x = Conv2D(96, (5, 5), padding='same', kernel_regularizer=l2(weight_decay), activation='relu')(inputs)
    x = BatchNormalization()(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)
    x = Dropout(0.3)(x)

    x = Conv2D(256, (5, 5), padding='same', kernel_regularizer=l2(weight_decay), activation='relu')(x)
    x = BatchNormalization()(x)
    x = MaxPooling2D(pool_size=(2, 2))(x)
    x = Dropout(0.4)(x)

    x = Conv2D(384, (5, 5), padding='same', kernel_regularizer=l2(weight_decay), activation='relu')(x)
    x = BatchNormalization()(x)
    x = Conv2D(384, (5, 5), padding='same', kernel_regularizer=l2(weight_decay), activation='relu')(x)
    x = BatchNormalization()(x)
    x = Conv2D(256, (5, 5), padding='same', kernel_regularizer=l2(weight_decay), activation='relu')(x)
    x = BatchNormalization()(x)
    x = Dropout(0.5)(x)

    x = Flatten()(x)
    x = Dense(1000, activation='relu', kernel_initializer='he_normal')(x)
    y = Dense(10, activation='softmax')(x)

    model = Model(inputs=inputs, outputs=y)
    model.compile(
        loss='categorical_crossentropy',
        optimizer='adam',
        metrics=['accuracy']
    )

    return model