FeiYull

icon location HK

Results 80 comments of FeiYull

多图推理问题

@Bruce-WangGF 多batch仅支持视频和摄像头

红外图像或者灰度图像的识别

@qqqe2 如果你的图像是类似灰度图的单通道图像，此时是不用的

By not providing "FindOpenCV.cmake" in CMAKE_MODULE_PATH this project has asked CMake to find a package configuration file provided by "OpenCV", but CMake did not find one. Could not find a package configuration file provided by "OpenCV" with any of the following names: OpenCVConfig.cmake opencv-config.cmake Add the installation prefix of "OpenCV" to CMAKE_PREFIX_PATH or set "OpenCV_DIR" to a directory containing one of the above files. If "OpenCV" provides a separate development package or SDK, be sure it has been installed.

@ningjianfeng install opencv: `sudo apt-get install libopencv-dev `

结果发生越界问题

@Ichiruchan 把越界时，那几个变量全部打印出来，同时把图片缓存下，单独调试，很可能是前面的问题导致m_output_objects_host值异常

YOLOv8-pose 出现编译错误 ，up帮忙看看给您磕头了

@KARAS1998 将tensorrt 安装目录下common/sample里面的sampleUtils.cpp文件添加到项目中，对应的头文件也包含到项目属性里面

onnx转换trt报错

@Yi-hash1 导出的onnx是静态输入，可参考仓库中导出onnx的指令

spend more than 20ms on prepocess on jetson nano, batch=1

@JinRanYAO Is the data you're testing a picture or a video?

spend more than 20ms on prepocess on jetson nano, batch=1

@JinRanYAO Try to use the following instructions to achieve fp16 quantization, and improve performance by about 100% ./trtexec --onnx=yolov8n-pose.onnx --saveEngine=yolov8n-pose-fp16.trt --buildOnly --minShapes=images:1x3x640x640 --optShapes=images:2x3x640x640 --maxShapes=images:4x3x640x640 --fp16 【FP32】: [04/07/2024-09:15:16] [I] preprocess time...

spend more than 20ms on prepocess on jetson nano, batch=1

@JinRanYAO It is recommended to enter the function YOLOv8Pose::preprocess to test the internal time overhead. [void YOLOv8Pose::preprocess(const std::vector& imgsBatch)](https://github.com/FeiYull/TensorRT-Alpha/blob/bca9575229ef5f6fe4c5acf51c1bd3c7e5959ec6/yolov8-pose/yolov8_pose.cpp#L103)

spend more than 20ms on prepocess on jetson nano, batch=1

@JinRanYAO U can merge the following operations to one: 1. resizeDevice 2. bgr2rgbDevice 3. normDevice Inside the resizeDevice's cuda kernel function you call, modify the following: [modify bofore] https://github.com/FeiYull/TensorRT-Alpha/blob/bca9575229ef5f6fe4c5acf51c1bd3c7e5959ec6/utils/kernel_function.cu#L142 [modify...