Backend agnostic image loading


I’m currently working on a Keras 3 version of the following tutorial: Handwriting recognition

I would like as much as possible to make the tuto executable regardless of the backend chosen.

In the current version of the tuto the images are loaded with the api Is there a way to load images efficiently with keras ?


Hi @Carceller_Pierre ,

As per your Requirement ,

You can use keras.utils.image_dataset_from_directory for loading the dataset present in your machine by proving the dataset path to it.

For your Reference Link

Thank You !