Views
No views yet
1pip install -U paddleocr
2pip install -U onnxruntime-gpupaddleocr layout_detection -i ./demo.jpg --model_name PP-DocLayoutV3 --engine onnxruntime1from paddleocr import LayoutDetection
2
3model = LayoutDetection(
4 model_name="PP-DocLayoutV3",
5 engine="onnxruntime",
6)
7output = model.predict("./demo.jpg", batch_size=1)
8for res in output:
9 res.print()
10 res.save_to_img(save_path="./output/")
11 res.save_to_json(save_path="./output/res.json")
1@misc{cui2026paddleocrvl15multitask09bvlm,
2 title={PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing},
3 author={Cheng Cui and Ting Sun and Suyin Liang and Tingquan Gao and Zelun Zhang and Jiaxuan Liu and Xueqing Wang and Changda Zhou and Hongen Liu and Manhui Lin and Yue Zhang and Yubo Zhang and Yi Liu and Dianhai Yu and Yanjun Ma},
4 year={2026},
5 eprint={2601.21957},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV},
8 url={https://arxiv.org/abs/2601.21957},
9}