Skip to main content

Getting started with Jupyter Notebook - Deep learning with python

Comments

Popular posts from this blog

Simple code for single image augmentation using Keras

Simple code for single image augmentation using Keras
from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img

datagen = ImageDataGenerator(
        rotation_range=20,
        width_shift_range=0.5,
        height_shift_range=0.5,
        shear_range=0.4,
        zoom_range=0.4,
        horizontal_flip=True,
        vertical_flip=True,
        fill_mode='nearest')

img = load_img('lb.png')  # this is a PIL image
x = img_to_array(img)  # this is a Numpy array with shape (3, 150, 150)
x = x.reshape((1,) + x.shape)  # this is a Numpy array with shape (1, 3, 150, 150)

# the .flow() command below generates batches of randomly transformed images
# and saves the results to the `preview/` directory
i = 0
for batch in datagen.flow(x, batch_size=1,
                          save_to_dir='preview', save_prefix='cat', save_format='jpeg'):
    i += 1
    if i > 10:
        break  # otherwise the generator would loop indefinitely

Python IDLE 3.7.0 - Learn Python

Relational Operators - Learn Python