tensorRT_Pro icon indicating copy to clipboard operation
tensorRT_Pro copied to clipboard

C++ library based on tensorrt integration

Results 98 tensorRT_Pro issues
Sort by recently updated
recently updated
newest added

编译环境根据readme.me文件中的要求配置的 想请教一下如何解决呢? [2022-09-29 15:28:01][error][trt_builder.cpp:30]:NVInfer: 1: [convolutionRunner.cpp::executeConv::458] Error Code 1: Cudnn (CUDNN_STATUS_EXECUTION_FAILED) [2022-09-29 15:28:01][fatal][trt_infer.cpp:356]:execute fail, code 0[cudaSuccess], message no error CMakeFiles/yolov7.dir/build.make:70: recipe for target 'CMakeFiles/yolov7' failed make[3]: *** [CMakeFiles/yolov7] Aborted (core...

``` [ 18%] Built target plugin_list Consolidate compiler generated dependencies of target pro [100%] Built target pro [2023-06-17 03:04:04][info][app_alphapose.cpp:36]:===================== test alphapose fp32 ================================== [2023-06-17 03:04:04][info][auto_download.cpp:11]:Auto download alpha-pose-136.onnx --2023-06-17 03:04:04-- http://zifuture.com:1556/fs/25.shared/alpha-pose-136.onnx...

Compile CXX src/tensorRT/onnx/onnx-operators-ml.pb.cpp /LoopHelpers.cpptensorRT/onnx_parser /LoopHelpers.hpp:5:0, /LoopHelpers.cpp:1: /ImporterContext.hpp:120:101: internal compiler error: invalid built-in macro "__FILE__" LOG_VERBOSE("Registering tensor: "

[2022-10-11 15:42:17][info][app_yolo.cpp:134]:===================== test YoloV5 FP32 yolov5s6 ================================== [2022-10-11 15:42:17][info][trt_builder.cpp:474]:Compile FP32 Onnx Model 'yolov5s6.onnx'. [2022-10-11 15:42:21][info][trt_builder.cpp:558]:Input shape is -1 x 3 x 640 x 640 [2022-10-11 15:42:21][info][trt_builder.cpp:559]:Set max batch size =...

CUDA Runtime error cudaSetDevice(device_id) # initialization error, code = cudaErrorInitializationError [ 3 ] in file /src/tensorRT/infer/trt_infer.cpp:472 请问下代码是否支持 这个是在jetson nx编译通过后,转engine是报错,麻烦大佬帮忙看看

支持yolov7实例分割吗?

../rtSafe/safeRuntime.cpp (25) - Cuda Error in allocate: 2 (out of memory) 请问在哪里调batch size

我使用的是yolo gpuptr版本,批量数据在添加到images_gpu时,host与device拷贝时间较长,大佬能否提供一下优化思路?

运行的时候提示没有opencv_world460d.dll nvinfer.dll cudart64_110.dll cublas64.dll ,可是我工程配置了啊,是不是原始工程中设置路径? 然后这些库只能放在c盘里面的System32 下面,配置了路径都没找到,而且复制到了debug下居然也不行