Thesis-NoiseDetection-CNN/classification_cnn_keras_cross_validation.py

'''This script goes along the blog post
"Building powerful image classification models using very little data"
from blog.keras.io.
```
data/
    train/
        final/
            final001.png
            final002.png
            ...
        noisy/
            noisy001.png
            noisy002.png
            ...
    validation/
        final/
            final001.png
            final002.png
            ...
        noisy/
            noisy001.png
            noisy002.png
            ...
```
'''
import sys, os, getopt

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, AveragePooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
from keras.utils import plot_model

from modules.model_helper import plot_info

# dimensions of our images.
img_width, img_height = 100, 100

train_data_dir = 'data/train'
validation_data_dir = 'data/validation'
nb_train_samples = 7200
nb_validation_samples = 3600
epochs = 50
batch_size = 16

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)



'''
Method which returns model to train
@return : DirectoryIterator
'''
def generate_model():
    # create your model using this function
    model = Sequential()
    model.add(Conv2D(60, (2, 2), input_shape=input_shape))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Conv2D(40, (2, 2)))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Conv2D(20, (2, 2)))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Conv2D(40, (2, 2)))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Conv2D(20, (2, 2)))
    model.add(Activation('relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))

    model.add(Flatten())

    model.add(Dense(256))
    model.add(Activation('relu'))
    model.add(Dropout(0.2))

    model.add(Dense(128))
    model.add(Activation('relu'))
    model.add(Dropout(0.2))

    model.add(Dense(64))
    model.add(Activation('relu'))
    model.add(Dropout(0.2))

    model.add(Dense(32))
    model.add(Activation('relu'))
    model.add(Dropout(0.05))

    model.add(Dense(1))
    model.add(Activation('sigmoid'))

    model.compile(loss='binary_crossentropy',
                  optimizer='rmsprop',
                  metrics=['accuracy'])

    return model

def load_data():
    # load your data using this function
    # this is the augmentation configuration we will use for training
    train_datagen = ImageDataGenerator(
        rescale=1. / 255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)

    train_generator = train_datagen.flow_from_directory(
        train_data_dir,
        target_size=(img_width, img_height),
        batch_size=batch_size,
        class_mode='binary')

    return train_generator

def train_and_evaluate_model(model, data_train, data_test):

    return model.fit_generator(
        data_train,
        steps_per_epoch=nb_train_samples // batch_size,
        epochs=epochs,
        shuffle=True,
        validation_data=data_test,
        validation_steps=nb_validation_samples // batch_size)

def main():

    global batch_size
    global epochs

    if len(sys.argv) <= 1:
        print('No output file defined...')
        print('classification_cnn_keras_svd.py --output xxxxx')
        sys.exit(2)
    try:
        opts, args = getopt.getopt(sys.argv[1:], "ho:b:e:d", ["help", "directory=", "output=", "batch_size=", "epochs="])
    except getopt.GetoptError:
        # print help information and exit:
        print('classification_cnn_keras_svd.py --output xxxxx')
        sys.exit(2)
    for o, a in opts:
        if o == "-h":
            print('classification_cnn_keras_svd.py --output xxxxx')
            sys.exit()
        elif o in ("-o", "--output"):
            filename = a
        elif o in ("-b", "--batch_size"):
            batch_size = int(a)
        elif o in ("-e", "--epochs"):
            epochs = int(a)
        elif o in ("-d", "--directory"):
            directory = a
        else:
            assert False, "unhandled option"


    # load of model
    model = generate_model()
    model.summary()

    n_folds = 10

    data_generator = ImageDataGenerator(rescale=1./255, validation_split=0.33)

    # check if possible to not do this thing each time
    train_generator = data_generator.flow_from_directory(train_data_dir, target_size=(img_width, img_height), shuffle=True, seed=13,
                                                         class_mode='binary', batch_size=batch_size, subset="training")

    validation_generator = data_generator.flow_from_directory(train_data_dir, target_size=(img_width, img_height), shuffle=True, seed=13,
                                                         class_mode='binary', batch_size=batch_size, subset="validation")

    # now run model
    history = train_and_evaluate_model(model, train_generator, validation_generator)

    print("directory %s " % directory)
    if(directory):
        print('Your model information will be saved into %s...' % directory)
    # if user needs output files
    if(filename):

        # update filename by folder
        if(directory):
            # create folder if necessary
            if not os.path.exists(directory):
                os.makedirs(directory)
            filename = directory + "/" + filename

        # save plot file history
        plot_info.save(history, filename)

        plot_model(model, to_file=str(('%s.png' % filename)))
        model.save_weights(str('%s.h5' % filename))

if __name__ == "__main__":
    main()