chunked/nltk_chunking/_preprocessing/chunk_82.txt

from datasets import load_dataset
dataset = load_dataset("food101", split="train[:100]")

Next, take a look at the image with 🤗 Datasets Image feature:

dataset[0]["image"]

Load the image processor with [AutoImageProcessor.from_pretrained]:

from transformers import AutoImageProcessor
image_processor = AutoImageProcessor.from_pretrained("google/vit-base-patch16-224")

First, let's add some image augmentation.