How do I Feed local Data (Images) into my Keras Network in Python?

Question

I am using the newest version of Tensorflow and Keras. I have seen the example where datasets like the MNIST ist loaded and used.

But how do I do this with local images?

Answer 1

You can also use ImageDataGenerator, which shuffles your data and can do augmentation for you (see https://keras.io/preprocessing/image/ ).

from keras.preprocessing.image import ImageDataGenerator

image_datagen = ImageDataGenerator(rescale=1./255)

image_generator = image_datagen.flow_from_directory(
    'your_training_images/train',
    target_size=(image_height, image_width),
    batch_size=batch_size,
    class_mode='binary')