使用ocr运行模板执行onnx加速报错

环境

• 【FastDeploy版本】：fastdeploy-linux-gpu-1.0.7

• 【编译命令】系统提供

• 【系统平台】: Linux x64(Ubuntu 18.04)

• 【硬件】： AI加速卡Tesla-V100-PCIE-32GB， CUDA 11.6 CUDNN 8.4

• 【编译语言】： C++

• 【模型跑不通】

• • 执行examples下的ONNX runtime部署示例会报错，其余示例均可正常执行,模型也为官方提供模型

• 【执行命令】

• • ./infer_demo ./ch_PP-OCRv3_det_infer ./ch_ppocr_mobile_v2.0_cls_infer ./ch_PP-OCRv3_rec_infer ./ppocr_keys_v1.txt ./12.jpg 6

• 【报错日志】

• • [WARNING] fastdeploy/runtime/runtime_option.cc(395)::SetTrtInputShape RuntimeOption::SetTrtInputShape will be removed in v1.2.0, please use RuntimeOption.trt_option.SetShape() instead.
    [WARNING] fastdeploy/runtime/runtime_option.cc(395)::SetTrtInputShape RuntimeOption::SetTrtInputShape will be removed in v1.2.0, please use RuntimeOption.trt_option.SetShape() instead.
    [WARNING] fastdeploy/runtime/runtime_option.cc(395)::SetTrtInputShape RuntimeOption::SetTrtInputShape will be removed in v1.2.0, please use RuntimeOption.trt_option.SetShape() instead.
    terminate called after throwing an instance of 'Ort::Exception'
    what(): /onnxruntime_src/onnxruntime/core/platform/posix/env.cc:183 onnxruntime::{anonymous}::PosixThread::PosixThread(const char*, int, unsigned int ()(int, Eigen::ThreadPoolInterface), Eigen::ThreadPoolInterface*, const onnxruntime::ThreadOptions&) pthread_setaffinity_np failed, error code: 17 error msg: File exists

Aborted

Start with the ONNX Runtime deployment example under examples and run the reported infer_demo command on the stated environment. Compare it with the working examples and inspect the pthread_setaffinity_np failure after the TensorRT deprecation warnings; done means the OCR template runs without the Ort::Exception and the cause or required configuration is documented.