RapidAI / RapidOCR

Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVION and PaddlePaddle. (将PaddleOCR模型做了转换,采用ONNXRuntime推理,速度很快)

Home Page:https://rapidai.github.io/RapidOCRDocs

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

关于rapidocr-openvino的pyinstaller打包问题

Hodoio opened this issue · comments

commented

使用版本:

  • rapidocr-openvino 1.2.10
  • openvino 2023.0.0

pyinstaller后出现错误:

Traceback (most recent call last):
  File "main.py", line 5, in <module>
  File "ocr\ocr.py", line 33, in ocr.ocr.main
  File "ocr\ocr.py", line 10, in ocr.ocr.OCR.__init__
  File "rapidocr_openvino\rapid_ocr_api.py", line 41, in __init__
  File "rapidocr_openvino\ch_ppocr_v3_det\text_detect.py", line 31, in __init__
  File "rapidocr_openvino\utils.py", line 25, in __init__
RuntimeError: Check 'false' failed at C:\Jenkins\workspace\private-ci\ie\build-windows-vs2019\b\repos\openvino\src\inference\src\core.cpp:100:
[ NETWORK_NOT_READ ] Unable to read the model: D:\Project\judges\build\lib.win-amd64-cpython-38\ocr\dist\main\rapidocr_openvino\models\ch_PP-OCRv3_det_infer.onnx Please check that model format: onnx is supported and the model is correct. Available frontends:

我已确认不是路径问题,config.yaml采用的是原包中的文件配置。
是否是我不可采用,或者需要对config.yaml进行修改?

commented

为什么加群,说来自Github,被拒绝?

commented

为什么加群,说来自Github,被拒绝?

可能你加的那个群满了,请加3群:450338158

commented

使用版本:

  • rapidocr-openvino 1.2.10
  • openvino 2023.0.0

pyinstaller后出现错误:

Traceback (most recent call last):
  File "main.py", line 5, in <module>
  File "ocr\ocr.py", line 33, in ocr.ocr.main
  File "ocr\ocr.py", line 10, in ocr.ocr.OCR.__init__
  File "rapidocr_openvino\rapid_ocr_api.py", line 41, in __init__
  File "rapidocr_openvino\ch_ppocr_v3_det\text_detect.py", line 31, in __init__
  File "rapidocr_openvino\utils.py", line 25, in __init__
RuntimeError: Check 'false' failed at C:\Jenkins\workspace\private-ci\ie\build-windows-vs2019\b\repos\openvino\src\inference\src\core.cpp:100:
[ NETWORK_NOT_READ ] Unable to read the model: D:\Project\judges\build\lib.win-amd64-cpython-38\ocr\dist\main\rapidocr_openvino\models\ch_PP-OCRv3_det_infer.onnx Please check that model format: onnx is supported and the model is correct. Available frontends:

我已确认不是路径问题,config.yaml采用的是原包中的文件配置。 是否是我不可采用,或者需要对config.yaml进行修改?

openvino打包,没有尝试过。可以参考onnxruntime版的打包 https://github.com/RapidAI/RapidOCR/blob/main/.github/workflows/package_ocrweb.yml

commented

issue先关闭了,后续有问题再开。