Create a function that combines image augmentation and image preprocessing for a batch of images and generates pixel_values:

def transforms(examples):
     images = [_transforms(img.convert("RGB")) for img in examples["image"]]
     examples["pixel_values"] = image_processor(images, do_resize=False, return_tensors="pt")["pixel_values"]
     return examples

In the example above we set do_resize=False because we have already resized the images in the image augmentation transformation,
and leveraged the size attribute from the appropriate image_processor.