chunked/nltk_chunking/tasks_image_classification/chunk_15.txt

images = [
         val_data_augmentation(convert_to_tf_tensor(image.convert("RGB"))) for image in example_batch["image"]
     ]
     example_batch["pixel_values"] = [tf.transpose(tf.squeeze(image)) for image in images]
     return example_batch

Use 🤗 Datasets [~datasets.Dataset.set_transform] to apply the transformations on the fly:
py
food["train"].set_transform(preprocess_train)
food["test"].set_transform(preprocess_val)
As a final preprocessing step, create a batch of examples using DefaultDataCollator.