Data

class segmentation.data.DataGenerator(id_list, batch_size=10, dim=(128, 128, 64), shuffle=True, n_classes=3)

Bases: tensorflow.python.keras.utils.data_utils.Sequence

Class used for data generators.

on_epoch_end()

Updates indexes after each epoch. If shuffle is set to True, the indexes are shuffled. Shuffling the order in which examples are fed to the classifier is helpful so that batches between epochs do not look alike. Doing so will eventually make our model more robust.

remapLabels(labels_4D)