/Image-Augmentation

(ImageDataGenerator) is Keras deep learning library provides the ability to use data augmentation automatically when training a model.

Primary LanguageJupyter Notebook

Image Augmentation in deep learning

(ImageDataGenerator) is Keras deep learning library provides the ability to use data augmentation automatically when training a model.

A range of techniques are supported, as well as pixel scaling methods. We will focus on five main types of data augmentation techniques for image data; specifically:

  • Image shifts via the width_shift_range and height_shift_range arguments.

  • Image flips via the horizontal_flip and vertical_flip arguments.

  • Image rotations via the rotation_range argument.

  • Image brightness via the brightness_range argument.

  • Image zoom via the zoom_range argument.

source: https://machinelearningmastery.com/how-to-configure-image-data-augmentation-when-training-deep-learning-neural-networks/