PP-OCRv3_rec识别推理模型转onnx再转openvino框架下ir文件出现错误

[cdycdycdy]

PP-OCRv3_rec官方识别推理模型转onnx再转openvino框架下IR文件出现以下错误：
Please install required versions of components or use install_prerequisites script
C:\Program Files (x86)\Intel\openvino_2021.3.394\deployment_tools\model_optimizer\install_prerequisites\install_prerequisites_onnx.bat
Note that install_prerequisites scripts may install additional components.
[ ERROR ] Cannot infer shapes or values for node "p2o.Mul.60".
[ ERROR ] The "beta" value for node p2o.Mul.60 must be a scalar
[ ERROR ]
[ ERROR ] It can happen due to bug in custom shape infer function <function Swish.infer at 0x000002352D4CAA60>.
[ ERROR ] Or because the node inputs have incorrect values/shapes.
[ ERROR ] Or because input shapes are incorrect (embedded to the model or passed via --input_shape).
[ ERROR ] Run Model Optimizer with --log_level=DEBUG for more information.
[ ERROR ] Exception occurred during running replacer "REPLACEMENT_ID" (<class 'extensions.middle.PartialInfer.PartialInfer'>): Stopped shape/value propagation at "p2o.Mul.60" node.
For more information please refer to Model Optimizer FAQ, question #38. (https://docs.openvinotoolkit.org/latest/openvino_docs_MO_DG_prepare_model_Model_Optimizer_FAQ.html?question=38#question-38)

麻烦大家帮忙看下，非常感谢

[tink2123]

可以直接试用 FastDeploy 在openvino下推理，参考 https://github.com/PaddlePaddle/FastDeploy/tree/develop/examples/vision/ocr/PP-OCRv3 下python/cpp代码使用即可，不需要再做模型转换

[tampe125]

@tink2123 I am having the same issue, can you please provide some guidance to convert it to OpenVino? I'd like to stick to the same framework instead of installing and configuring a whole new framework

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.