bug描述 Describe the Bug

cuda:10.2
cudnn:8.3
tensortRT:7.2.3.4
paddle預測庫：manylinux_cuda10.2_cudnn8.1_avx_mkl_trt7_gcc5.4
系統：unbuntu16

問題描述：運行一段時間，檢測幾張圖片後，程序就退出崩潰。
崩潰信息：

C++ Traceback (most recent call last):

0 PaddleOCR::DBDetector::Run(cv::Mat&, std::vector<std::vector<std::vector<int, std::allocator >, std::allocator<std::vector<int, std::allocator > > >, std::allocator<std::vector<std::vector<int, std::allocator >, std::allocator<std::vector<int, std::allocator > > > > >&, std::vector<double, std::allocator >*)
1 void paddle_infer::Tensor::CopyFromCpu(float const*)
2 paddle::platform::DeviceContextPool::Get(paddle::platform::Place const&)
3 std::__future_base::_Deferred_state<std::_Bind_simple<void paddle::platform::EmplaceDeviceContext<paddle::platform::CUDADeviceContext, paddle::platform::CUDAPlace>(std::map<paddle::platform::Place, std::shared_future<std::unique_ptr<paddle::platform::DeviceContext, std::default_deletepaddle::platform::DeviceContext > >, std::lesspaddle::platform::Place, std::allocator<std::pair<paddle::platform::Place const, std::shared_future<std::unique_ptr<paddle::platform::DeviceContext, std::default_deletepaddle::platform::DeviceContext > > > > >, paddle::platform::Place)::{lambda() #1 } ()>, std::unique_ptr<paddle::platform::DeviceContext, std::default_deletepaddle::platform::DeviceContext > >::_M_complete_async()
4 std::_Function_handler<std::unique_ptr<std::__future_base::_Result_base, std::__future_base::_Result_base::_Deleter> (), std::__future_base::_Task_setter<std::unique_ptr<std::__future_base::_Result<std::unique_ptr<paddle::platform::DeviceContext, std::default_deletepaddle::platform::DeviceContext > >, std::__future_base::_Result_base::_Deleter>, std::_Bind_simple<void paddle::platform::EmplaceDeviceContext<paddle::platform::CUDADeviceContext, paddle::platform::CUDAPlace>(std::map<paddle::platform::Place, std::shared_future<std::unique_ptr<paddle::platform::DeviceContext, std::default_deletepaddle::platform::DeviceContext > >, std::lesspaddle::platform::Place, std::allocator<std::pair<paddle::platform::Place const, std::shared_future<std::unique_ptr<paddle::platform::DeviceContext, std::default_deletepaddle::platform::DeviceContext > > > > >, paddle::platform::Place)::{lambda() #1 } ()>, std::unique_ptr<paddle::platform::DeviceContext, std::default_deletepaddle::platform::DeviceContext > > >::_M_invoke(std::_Any_data const&)
5 paddle::platform::CUDADeviceContext::CUDADeviceContext(paddle::platform::CUDAPlace)
6 paddle::platform::CUDAContext::CUDAContext(paddle::platform::CUDAPlace const&, paddle::platform::stream::Priority const&, paddle::platform::stream::StreamFlag const&)
7 paddle::platform::CublasHandleHolder::CublasHandleHolder(CUstream_st*, cublasMath_t)
8 paddle::platform::EnforceNotMet::EnforceNotMet(paddle::platform::ErrorSummary const&, char const*, int)
9 paddle::platform::GetCurrentTraceBackString abi:cxx11

Error Message Summary:

ExternalError: CUBLAS error(1).
[Hint: Please search for the error code(1) on website (https://docs.nvidia.com/cuda/cublas/index.html#cublasstatus_t) to get Nvidia's official solution and advice about CUBLAS Error.] (at /paddle/paddle/fluid/platform/cuda_helper.h:98)

其他补充信息 Additional Supplementary Information

• No response*