PaddleOCR/main/version2.x/ppstructure/blog/return_word_pos

[giscus[bot]]

PaddleOCR/main/version2.x/ppstructure/blog/return_word_pos

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

https://paddlepaddle.github.io/PaddleOCR/main/version2.x/ppstructure/blog/return_word_pos.html

[zzsyppt]

按照文档操作出现如下报错，请问是什么原因？（推理模型都采用的文档中的模型）[2025/05/25 14:28:08] ppocr WARNING: The first GPU is used for inference by default, GPU ID: 0
Traceback (most recent call last):
File "E:\PaddleOCR\ppstructure\predict_system.py", line 415, in
main(args)
File "E:\PaddleOCR\ppstructure\predict_system.py", line 310, in main
structure_sys = StructureSystem(args)
File "E:\PaddleOCR\ppstructure\predict_system.py", line 73, in init
self.text_system = TextSystem(args)
File "E:\PaddleOCR\tools\infer\predict_system.py", line 53, in init
self.text_detector = predict_det.TextDetector(args)
File "E:\PaddleOCR\tools\infer\predict_det.py", line 42, in init
raise ValueError(
ValueError: PP-OCRv3_mobile_det is not supported. Please check if the model is supported by the PaddleOCR wheel.

[zzsyppt]

切换到release/2.10分支解决了