How to use PaddlePaddle/PP-DocLayoutV3 with PaddleOCR:
# 1. See https://www.paddlepaddle.org.cn/en/install to install paddlepaddle # 2. pip install paddleocr from paddleocr import LayoutDetection model = LayoutDetection(model_name="PP-DocLayoutV3") output = model.predict(input="path/to/image.png", batch_size=1) for res in output: res.print() res.save_to_img(save_path="./output/") res.save_to_json(save_path="./output/res.json")
I need a model that could take in a PDF page, and output bounding boxes for paragraphs and images, in some machine readable form, perhaps JSON.
Can this model do this?
Regards.
· Sign up or log in to comment
