data_augmentation_save_images.py

#import all dependencies
import PIL 
from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
import numpy as np


datagen = ImageDataGenerator(
        rotation_range=40,
        width_shift_range=0.2,
        height_shift_range=0.2,
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True,
        fill_mode='nearest')

if __name__ == '__main__':

    image_file_path = "dataset/train/dog/dog.01.jpg"

    img = load_img(image_file_path) 
    image_array = img_to_array(img) 
    
    x = image_array.reshape((1,) + image_array.shape)

    # compute quantities required for featurewise normalization
    # (std, mean, and principal components if ZCA whitening is applied)
    datagen.fit(x)
    
    i = 0

    for batch in datagen.flow(x,save_to_dir='path_augmented_image_folder', save_prefix='Dog', save_format='jpeg'):
        i += 1
        print ("Image count--->",i)
        if i >= 20:
            print ("Saved 20 augmented images succesfully")
            break