| image_processor = processor.image_processor | |
| def get_ocr_words_and_boxes(examples): | |
| images = [image.convert("RGB") for image in examples["image"]] | |
| encoded_inputs = image_processor(images) | |
| examples["image"] = encoded_inputs.pixel_values | |
| examples["words"] = encoded_inputs.words | |
| examples["boxes"] = encoded_inputs.boxes | |
| return examples | |
| To apply this preprocessing to the entire dataset in a fast way, use [~datasets.Dataset.map]. |