Urgent update needed: image_dataset_from_directory and preprocessing layers

Course Q&A TensorFlow Developer Professional Convolutional Neural Networks in TensorFlow
1

Just been looking at the tensorflow documentation (below). The ImageDataGenerator is now deprecated for new code.

The use of image_dataset_from_directory and preprocessing layers is advised, and I assume required for the Tensorflow Professional Certificate exam.

Please urgently provide a summary of the changes needed to notebook workflows when using the recommended methods, and simple examples.

Many thanks!

==================================================================

tf.keras.preprocessing.image.ImageDataGenerator

Deprecated: tf.keras.preprocessing.image.ImageDataGenerator is not recommended for new code. Prefer loading images with tf.keras.utils.image_dataset_from_directory and transforming the output tf.data.Dataset with preprocessing layers. For more information, see the tutorials for loading images and augmenting images, as well as the preprocessing layer guide.

2

Please see this line in section 3, 6th point of the exam handbook
Use ImageDataGenerator.

This course uses version 2.7 which doesn’t deprecate this API.

2 Likes