Why do you divide the data set like this?

[Cds3851]

X_train, X_test, y_train, y_test = train_test_split(images, labels, test_size=0.3, random_state=random.randint(0, 100)) X_valid, X_test, y_valid, y_test = train_test_split(images, labels, test_size=0.5, random_state=random.randint(0, 100))