from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K

img_width, img_height = 256, 256

train_data_dir = 'data/train'
validation_data_dir = 'data/validation'
nb_train_samples = 140
nb_validation_samples = 40
epochs = 20
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)

model = Sequential()
model.add(Conv2D(32, (2, 2), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (2, 2)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (2, 2)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))

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

train_datagen = ImageDataGenerator(
        rotation_range=45,
        width_shift_range=0.3,
        height_shift_range=0.3,
        rescale=1./255,
        shear_range=0.25,
        zoom_range=0.1,
        horizontal_flip=True)

validation_datagen = ImageDataGenerator(rescale=1. / 255)

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

validation_generator = validation_datagen.flow_from_directory(
        validation_data_dir,
        target_size=(img_width, img_height),
        batch_size=batch_size,
        class_mode='binary')

model.fit_generator(
        train_generator,
        steps_per_epoch=nb_train_samples // batch_size,
        epochs=epochs,
        validation_data=validation_generator,
        validation_steps=nb_validation_samples // batch_size)

model.save_weights('model_food_dirty.h5')
results = model.evaluate(train_generator)
print(results)

'''     test na pojedynczym elemencie
test_image = load_img('data/train/dirty/dirty016.png', target_size=(img_width, img_height))
test_image = img_to_array(test_image)
test_image = test_image.reshape((1,) + test_image.shape)

# 0 -> dirty, 1 -> food

result = model.predict(test_image)
print(result)
'''