# example of zoom image augmentation
from numpy import expand_dims
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array
from keras.preprocessing.image import ImageDataGenerator
from matplotlib import pyplot
# load the image
#img = load_img('bird.jpg')
# convert to numpy array
#data = img_to_array(img)
# expand dimension to one sample
#samples = expand_dims(data, 0)
# create image data augmentation generator
#datagen = ImageDataGenerator(zoom_range=[0.5,0.8])
datagen = ImageDataGenerator(
        rotation_range=5,
        width_shift_range=0.1,
        height_shift_range=0.1,
        rescale=1./255,
        shear_range=0.1,
        zoom_range=0.1,
        horizontal_flip=False,
        fill_mode='nearest')

# prepare iterator
#it = datagen.flow(samples, batch_size=1)
it = datagen.flow_from_directory('aug/', target_size=(128, 128), save_to_dir='trained/', save_prefix='gen_', batch_size=10, class_mode='binary')


# generate samples and plot
for i in range(1000):
	# define subplot
	#pyplot.subplot(330 + 1 + i)
	# generate batch of images
	batch = it.next()
	print('batch type:', type(batch))
	# convert to unsigned integers for viewing
	#image = batch[0].astype('uint8')
	#print('image type:', type(image))
	# plot raw pixel data
	#pyplot.plot(image)
	#pyplot.imshow(image)
# show the figure
#pyplot.show()
#These are just a few of the options available (for more, see the documentation). Let's quickly go over what we just wrote:

#rotation_range is a value in degrees (0-180), a range within which to randomly rotate pictures
#width_shift and height_shift are ranges (as a fraction of total width or height) within which to randomly translate pictures vertically or horizontally
#rescale is a value by which we will multiply the data before any other processing. Our original images consist in RGB coefficients in the 0-255, but such values would be too high for our models to process (given a typical learning rate), so we target values between 0 and 1 instead by scaling with a 1/255. factor.
#shear_range is for randomly applying shearing transformations
#zoom_range is for randomly zooming inside pictures
#horizontal_flip is for randomly flipping half of the images horizontally --relevant when there are no assumptions of horizontal assymetry (e.g. real-world pictures).
#fill_mode is the strategy used for filling in newly created pixels, which can appear after a rotation or a width/height shift.