cnn with augmentation.py

X, X_test, y, y_test = get_data()

batch_size = 32
num_classes = 2
epochs = 400
data_augmentation = False

# Convert class vectors to binary class matrices.
y_train = keras.utils.to_categorical(y, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential([
    Conv2D(32, (3, 3), padding='same', input_shape=X.shape[1:], activation='relu'),
    Conv2D(32, (3, 3), padding='same', activation='relu'),
    MaxPooling2D(pool_size=(2, 2)),
    
    Conv2D(128, (3, 3), padding='same', activation='relu'),
    Conv2D(128, (3, 3), padding='same',activation='relu'),
    MaxPooling2D(pool_size=(2, 2)),

    Conv2D(256, (3, 3), padding='same', activation='relu'),
    Conv2D(256, (3, 3), padding='same', activation='relu'),
    MaxPooling2D(pool_size=(2, 2)),
    
#     Conv2D(512, (3, 3), padding='same', activation='relu'),
#     Conv2D(512, (3, 3), padding='same', activation='relu'),
#     MaxPooling2D(pool_size=(2, 2)),
    
    Flatten(),
    Dense(1024, activation='relu'),
    Dropout(0.5),
    Dense(1024, activation='relu'),
    Dropout(0.5),
    Dense(num_classes),
    Activation('softmax'),
])

# initiate RMSprop optimizer
opt = keras.optimizers.rmsprop(lr=1e-5, decay=1e-6)

# Let's train the model using RMSprop
model.compile(loss='categorical_crossentropy',
              optimizer=opt,
              metrics=['accuracy'])

x_train = X.astype('float32')
x_test = X_test.astype('float32')
x_train /= 255
x_test /= 255

checkpointer = ModelCheckpoint(filepath='tmp\\weights.hdf5', verbose=1, save_best_only=True)


if not data_augmentation:
    print('Not using data augmentation.')
    history = model.fit(x_train, y_train,
              batch_size=batch_size,
              epochs=epochs,
              validation_data=(x_test, y_test),
              callbacks=[checkpointer])

else:

    print('Using real-time data augmentation.')
    # This will do preprocessing and realtime data augmentation:
    datagen = ImageDataGenerator(
        featurewise_center=False,  # set input mean to 0 over the dataset
        samplewise_center=False,  # set each sample mean to 0
        featurewise_std_normalization=False,  # divide inputs by std of the dataset
        samplewise_std_normalization=False,  # divide each input by its std
        zca_whitening=False,  # apply ZCA whitening
        rotation_range=0,  # randomly rotate images in the range (degrees, 0 to 180)
        width_shift_range=0.1,  # randomly shift images horizontally (fraction of total width)
        height_shift_range=0.1,  # randomly shift images vertically (fraction of total height)
        horizontal_flip=True,  # randomly flip images
        vertical_flip=False)  # randomly flip images


    # Compute quantities required for feature-wise normalization
    # (std, mean, and principal components if ZCA whitening is applied).
    datagen.fit(x_train)

    # Fit the model on the batches generated by datagen.flow().
    history = model.fit_generator(datagen.flow(x_train, y_train,
                                     batch_size=batch_size),
                        steps_per_epoch=x_train.shape[0] // batch_size,
                        epochs=epochs,
                        validation_data=(x_test, y_test),
                        callbacks=[checkpointer])