使用paddle_inference.dll 最新版，开启TensorRT, 推理paddleocr, 出错。

[yjszyd0813]

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem

• 系统环境/System Environment：
• 版本号/Version：Paddle：2.4.2 PaddleOCR：2.6.2 问题相关组件/Related components：
• 运行指令/Command Code：
• 完整报错/Complete Error Message：

[runtime.cpp::nvinfer1::Runtime::~Runtime::346] Error Code 3: API Usage Error (Parameter check failed at: runtime.cpp::nvinfer1::Runtime::~Runtime::346, condition: mEngineCounter.use_count() == 1. Destroying a runtime before destroying deserialized engines created by the runtime leads to undefined behavior.

这个错误是因为什么？ 开启TensorRT，总是会中断 build tensorrt engine

[heguyu]

我的也是
Error Code 3: API Usage Error (Parameter check failed at: runtime.cpp::nvinfer1::Runtime::~Runtime::346, condition: mEngineCounter.use_count() == 1. Destroying a runtime before destroying deserialized engines created by the runtime leads to undefined behavior.
)

[mrchengshunlong]

@yjszyd0813 @heguyu 我解决了，但不知道是哪个起的作用，我在PaddleOCR加入了参数max_text_length=40,use_dynamic_shape=True ，并且将将zlibwapi.dll添加到C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2\bin ，将zlibwapi.lib添加到C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.2\lib\x64
这是zlib123dll.zip 的地址，希望可以帮到你们

[github-actions]

This issue is stale because it has been open for 90 days with no activity.