Deep Learning with Applications Using Python: Chatbots and Face, Object, and Speech Recognition With TensorFlow and Keras

Appendix 1: Keras Functions for Image Processing

Keras has a function called ImageDataGenerator that provides you with batches of tensor image data with real-time data augmentation. Data will be looped over in batches indefinitely.

Here is the function:

Here are the function’s arguments:

• featurewise_center : Data type boolean . Sets input mean to 0 over the data set, feature-wise.

• samplewise_center : Data type boolean . Sets each sample mean to 0.

• featurewise_std_normalization : Data type boolean . Divides inputs by std of the data set, feature-wise.

• samplewise_std_normalization : Data type boolean . Divides each input by its std .