Do you plan to support batch processing??

Hi,thank for your shareing. But i have some problems when I cmake in win10.
here is my cmakelist(only build retinaface):

cmake_minimum_required(VERSION 3.5)
project(tensorRT)
set_property(GLOBAL PROPERTY USE_FOLDERS on)

output

set(EXECUTABLE_OUTPUT_PATH "${PROJECT_BINARY_DIR}/bin")
message(STATUS "Project_binary_dir : ${PROJECT_BINARY_DIR}")

c++ 11

set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")

tensorRT

set(tensorrt_dir D:/c/TensorRT-7.0.0.11.Windows10.x86_64.cuda-10.0.cudnn7.6/TensorRT-7.0.0.11)
set(project_dir my/path/to/tensorRT-7)
include_directories(${tensorrt_dir}/include)
include_directories(${project_dir}/include)
link_directories(${tensorrt_dir}/lib)
link_directories(${project_dir}/source)
link_directories(${project_dir}/lib)

Loggers

aux_source_directory(${common_dir}/source common_src)
set(COMMON_SRC ${common_src} CACHE INTERNAL "common_source" )
set(LOGGER_SRC ${common_dir}/source/logger.cpp CACHE INTERNAL "logger" )

message(STATUS "TensorRT Header => ${tensorrt_dir}/include")
message(STATUS "TensorRT Lib => ${tensorrt_dir}/lib")

find opencv

find_package(OpenCV REQUIRED)
include_directories(${OpenCV_INCLUDE_DIRS})
if(NOT OpenCV_LIBRARY_DIRS)
set(OpenCV_LIBRARY_DIRS D:/software/opencv/build/x64/vc14/lib)
message(WARING " Can not find opencv lib. It will use the default path => ${OpenCV_LIBRARY_DIRS}")
endif()
link_directories(${OpenCV_LIBRARY_DIRS})
message(STATUS "OpenCV_INCLUDE_DIRS => ${OpenCV_INCLUDE_DIRS}")
message(STATUS "OpenCV_LIBRARY_DIRS => ${OpenCV_LIBRARY_DIRS}")

if(NOT OpenCV_FOUND)
message(ERROR "OpenCV not found!")
endif(NOT OpenCV_FOUND)

find cuda

find_package(CUDA)
find_package(CUDA REQUIRED)

#include_directories(${CUDA_INCLUDE_DIRS})
include_directories(C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v10.0/include)
if(NOT CUDA_LIBRARY_DIRS)
set(CUDA_LIBRARY_DIRS C:/Program Files/NVIDIA GPU Computing Toolkit/CUDA/v10.0/lib/x64)
message(WARING " Can not find CUDA lib. It will use the default path => ${CUDA_LIBRARY_DIRS}")
endif()
link_directories(${CUDA_LIBRARY_DIRS})
message(STATUS "CUDA_INCLUDE_DIRS : ${CUDA_INCLUDE_DIRS}")
message(STATUS "CUDA_LIBRARY_DIRS : ${CUDA_LIBRARY_DIRS}")

###############################################
set(CMAKE_LIBRARY_OUTPUT_DIRECTORY ${project_dir}/lib)
set(TRT source/tensorrt.cpp source/logger.cpp source/utils.cpp source/utils.cu)
set(INT8 source/Int8Calibrator.cu source/Int8Calibrator.cpp)

set(RETINAFACE ${TRT} ${INT8} source/retinaface.cpp)

set(CV_LIB libopencv_core.so libopencv_imgproc.so libopencv_imgcodecs.so)
set(TRT_LIB libnvinfer.so libnvonnxparser.so cudart.so)

cuda_add_executable(retinaface retinaface_main.cpp)
target_link_libraries(retinaface retinafacetrt.so ${TRT_LIB} ${CV_LIB})

#########################3#####################
cuda_add_library(retinafacetrt SHARED ${RETINAFACE})

the "set(project_dir /work/tensorRT-7) ",what is means of the file :tensorRT-7? I can not generate this and find in gits file.

I can cmake/build successfully with compiler VNC14 and generate tensorRT.sln. BUT, it can not open retinaface.h when I debug the .sln, fatal error: no such file in retinaface.vcxproj.
and do not generate retinafaceInt8.calibration and retinafaceInt8.calibration.
so what should I do for compiling in win10?

hi，fcos.cpp的45行，
float tmp = sigmoid(cls_f[pos*length+c]) * cen_f[pos];

是不是应该写成
float tmp = sigmoid(cls_f[pos+length*c]) * cen_f[pos];

hi, could you please tell me how can I get CalibrationTablePath file and SerializedPath file?
Thanks, look forward for your reply

可以加个联系方式吗,xiong97531,wechat num

如题: https://github.com/Syencil/tensorflow-yolov3没有了，能否重新上传您的项目，我使用原版代码无法完成.pb到.onnx的转换,您可以分享一下么

参考以下编译，报错。其中执行make + project_lib或make + project_name会报make: *** 没有规则可制作目标“+”。 停止。错误。

mkdir build
cd build
cmake -DCMAKE_BUILD_TYPE=Release ..
make + project_lib
make + project_name
./bin/project_name

如果直接make报以下错误，请问如何解决或者对依赖库有版本要求

[ 28%] Linking CXX executable bin/stream
/usr/bin/ld: 找不到 -lnvinfer
/usr/bin/ld: 找不到 -lnvonnxparser
/usr/bin/ld: 找不到 -lnvinfer
/usr/bin/ld: 找不到 -lnvonnxparser
collect2: error: ld returned 1 exit status
make[2]: *** [CMakeFiles/stream.dir/build.make:129：bin/stream] 错误 1
make[1]: *** [CMakeFiles/Makefile2:184：CMakeFiles/stream.dir/all] 错误 2
make: *** [Makefile:84：all] 错误 2

jetson Xavier NX，jetpack 4.5， cuda10.2，tensor rt 7.1.3

cmake之后直接make，报错：

[ 31%] Linking CXX executable bin/fcos
/usr/bin/ld: cannot find -lfcostrt
/usr/bin/ld: cannot find -llibnvinfer.so.7.1.3
/usr/bin/ld: cannot find -llibnvonnxparser.so.7.1.3
collect2: error: ld returned 1 exit status
CMakeFiles/fcos.dir/build.make:113: recipe for target 'bin/fcos' failed
make[2]: *** [bin/fcos] Error 1
CMakeFiles/Makefile2:215: recipe for target 'CMakeFiles/fcos.dir/all' failed
make[1]: *** [CMakeFiles/fcos.dir/all] Error 2
Makefile:83: recipe for target 'all' failed
make: *** [all] Error 2

我将CMakeLists.txt中的第56行：
set(TRT_LIB libnvinfer.so.7.0.0 libnvonnxparser.so.7.0.0 cuda.so)
改为：
set(TRT_LIB /usr/lib/aarch64-linux-gnu/libnvinfer.so.7.1.3 /usr/lib/aarch64-linux-gnu/libnvonnxparser.so.7.1.3 cuda.so)
说明：我的libnvinfer.so文件在/usr/lib/aarch64-linux-gnu/位置，并且版本是7.1.3，并没有找到7.0.0，所以修改了版本和位置。

然后再make，报错：

[ 31%] Linking CXX executable bin/fcos
/usr/bin/ld: cannot find -lfcostrt
collect2: error: ld returned 1 exit status
CMakeFiles/fcos.dir/build.make:117: recipe for target 'bin/fcos' failed
make[2]: *** [bin/fcos] Error 1
CMakeFiles/Makefile2:215: recipe for target 'CMakeFiles/fcos.dir/all' failed
make[1]: *** [CMakeFiles/fcos.dir/all] Error 2
Makefile:83: recipe for target 'all' failed
make: *** [all] Error 2

比之前少了两行，但还是没有生成libfcostrt.so这个文件。

如题

主要存在两个问题，求解答：
1、在问题#11中，对于yolov5s转换完的模型出现检测出来的目标少于python的问题，您指出是预处理方式的问题，请问具体如何修改？是否有尝试结果？
2、在运行转换好的trt模型时，出现如下的报错
[11/18/2020-14:24:13] [W] [TRT] onnx2trt_utils.cpp:220: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[11/18/2020-14:24:13] [W] [TRT] onnx2trt_utils.cpp:246: One or more weights outside the range of INT32 was clamped
[11/18/2020-14:24:13] [W] [TRT] onnx2trt_utils.cpp:246: One or more weights outside the range of INT32 was clamped
[11/18/2020-14:24:13] [W] [TRT] onnx2trt_utils.cpp:246: One or more weights outside the range of INT32 was clamped
[11/18/2020-14:24:13] [W] [TRT] onnx2trt_utils.cpp:246: One or more weights outside the range of INT32 was clamped
[11/18/2020-14:24:13] [W] [TRT] onnx2trt_utils.cpp:246: One or more weights outside the range of INT32 was clamped
[11/18/2020-14:24:13] [W] [TRT] onnx2trt_utils.cpp:246: One or more weights outside the range of INT32 was clamped
[11/18/2020-14:24:13] [W] [TRT] onnx2trt_utils.cpp:246: One or more weights outside the range of INT32 was clamped
[11/18/2020-14:24:13] [W] [TRT] onnx2trt_utils.cpp:246: One or more weights outside the range of INT32 was clamped
[11/18/2020-14:24:17] [I] [TRT] Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.
这个能够有比较简单的方法解决吗？还是需要去原始模型代码中转换相关部分的数据类型？

大佬，我自己尝试将U版的yolov3转onnx转tensorRT，但是测到的速度在pytorch原版上是推理20ms一张图而在tensorRT推理也是差不多这个速度。请问要如何加速呀？转int8吗？

Hi there! Thank you for your excellent codes and it helps me a lot. I trained a network with pytorch and deployed it with tensorRT successfully. But the infer time (do NOT include pre/post process) got longer compared to inferring in torch. While converted to INT8 the model is getting faster but not enough. Is that normal? Maybe there is something I missed while deploying the model. I have no idea about it and can you hint me with any ideas?
GPU: GTX1080Ti/CUDA10.0
Model: DeeplabV3Plus with backbone ResNet50
pytorch1.6 infer time 15ms
tensorrt infer time 22ms/FP32, 13ms/INT8

大佬，我想问一下，就是数据预处理那，cv2直接读图是BGR格式，但是原工程训练时候用的是RGB格式，不转成RGB没有问题吗？

您好，fp32测试是正常出框的，int8量化后不出框是怎么回事？

tensorrt是deb安装的么？谢谢

@Syencil

Is this repo has implementation for hand pose keypoints detection?

please advise

大佬，请问Psenet转trt的代码方便提供一份不？

如题，谢谢！

tensorRT6.0 尝试有问题，编译加载pytorch的onnx，会有问题

[ 20%] Linking CXX executable bin/yolo5
/usr/bin/ld: 找不到 -lyolo5trt

这个报错找不到yolo5trt库是什么原因？
cmakelist.txt里面还有哪些要改

@Syencil Hi there,
i have a task dealing with text detection.
are you available for freelancing?
if so contact me by my email so i can share with you more information.
[email protected]

in make:
not found yolov5trt

大佬好，感谢大佬的工作

我是从您那个轻量化 yolov5s 来的，用的也是您那个 yolov5s_voc 的代码，放到这个工程里面，都是可以成功运行的，但是最后预测完图片上啥也没有，打印了一下 bboxs 大小也是 0

求教大佬这个该如何解决

再次感谢！

ONNX IR version: 0.0.6
Opset version: 11
Producer name: pytorch
Producer version: 1.5
Domain:
Model version: 0

While parsing node number 108 [Resize]:
ERROR: ModelImporter.cpp:124 In function parseGraph:
[5] Assertion failed: ctx->tensors().count(inputName)
[08/12/2020-10:45:42] [E] Parsing File Failed
[08/12/2020-10:45:42] [E] Init Session Failed!
Segmentation fault (core dumped)

I have check the print export_onnx_model. no %108.

if I choose Opset version=12, the print of export_onnx_model.:%108:Long()
but,the same error counted

Hey @Syencil .
First of all thank you for the awesome code samples.

RetinaFace sample works well on TensorRT 7.1.3 with Cuda 11 but fails with no detection on Jetson Nano (TRT 7.1.3 & Cuda 10.2).

Can you help me in this regard?

hi there,

when I do the cmake . step, error pops up like:

CMake Error at /opt/cmake-3.12.2-Linux-x86_64/share/cmake-3.12/Modules/FindCUDA.cmake:1816 (add_library):
Cannot find source file:
source/ctpn.cpp

please help, thanks!

hello，I follow the Quick Start，and get yolov5s.onnx from https://github.com/Syencil/mobile-yolov5-pruning-distillation, when run the ./bin/yolov5 raise the error "Found unsupported datatype (11) when importing initializer: model.0.conv.total_ops". I check the onnx export log, "DOUBLE" datatype exists, may be this lead to error, how can i solve this, any help will be appreciated.
I use the pytorch1.4 and TensorRT7.1.3.4.

作者你好，我有一个问题，是关于把pse算法的onnx模型转换到pb模型，遇到的一个问题：
**Traceback (most recent call last):
File "/home/fffan/fffan_files/Experiment/Example/onnx2pb/onnx2pb.py", line 45, in
onnx2pb_2(onnx_input_path)
File "/home/fffan/fffan_files/Experiment/Example/onnx2pb/onnx2pb.py", line 14, in onnx2pb_2
tf_rep = prepare(model)
File "/home/fffan/下载/onnx-tensorflow-tf-1.x/onnx_tf/backend.py", line 65, in prepare
return cls.onnx_model_to_tensorflow_rep(model, strict)
File "/home/fffan/下载/onnx-tensorflow-tf-1.x/onnx_tf/backend.py", line 85, in onnx_model_to_tensorflow_rep
return cls._onnx_graph_to_tensorflow_rep(model.graph, opset_import, strict)
File "/home/fffan/下载/onnx-tensorflow-tf-1.x/onnx_tf/backend.py", line 146, in _onnx_graph_to_tensorflow_rep
strict=strict)
File "/home/fffan/下载/onnx-tensorflow-tf-1.x/onnx_tf/backend.py", line 241, in _onnx_node_to_tensorflow_op
return handler.handle(node, tensor_dict=tensor_dict, strict=strict)
File "/home/fffan/下载/onnx-tensorflow-tf-1.x/onnx_tf/handlers/handler.py", line 60, in handle
cls.args_check(node, kwargs)
File "/home/fffan/下载/onnx-tensorflow-tf-1.x/onnx_tf/handlers/backend/resize.py", line 89, in args_check
"Tensorflow")
File "/home/fffan/下载/onnx-tensorflow-tf-1.x/onnx_tf/common/exception.py", line 50, in call
raise self._func(self.get_message(op, framework))
RuntimeError: Resize coordinate_transformation_mode=pytorch_half_pixel is not supported in Tensorflow.
我没看到载pytorch有关pytorch_half_pixel这个的使用，但是转换模型的时候总是这个错。请问作者能不能解决这个问题？
非常期待作者的回复。

你好，请问你将mmdetection中Retinanet的模型转换为onnx是使用mmdetection提供的工具转换的吗？

作者你好，对于TRT不支持的层是如何处理的呢？ 比如Unsample层？ 期待回复

运行yolov5代码，报错

double free or corruption (out)

通过删减代码，执行前处理和推理过程后会报此类错误，重复释放内存问题

还是说只能对yolov5x.pt进行加速？

在tf2中如何将yolov3转换为冻结图，并生成对应的.pb文件？

The problem is that I can not parse the yolov5 model

the error is

While parsing node number 176 [Resize]:
ERROR: ModelImporter.cpp:124 In function parseGraph:
[5] Assertion failed: ctx->tensors().count(inputName)
[07/28/2021-11:07:41] [E] Parsing File Failed
[07/28/2021-11:07:41] [E] Init Session Failed!
Segmentation fault

My environment

Tensorrt 7.0
cuda 10.2
opencv 3.4

I hope I can get some help, thanks !

这样可以跑一跑代码

你好! psenetv2 里面 trtParams.CalibrationTablePath和trtParams.SerializedPath这两个参数是怎么定的

for (auto &future : futures) {
            future = mThreadPool.submit(&Yolov5::postProcessParall, this, block_start, block_size, height, width, scale_idx, postThres, origin_output, &bboxes);
            block_start += block_size;
        }
        this->postProcessParall(block_start, height-block_start, height, width, scale_idx, postThres, origin_output, &bboxes);
        for (auto &future : futures){
            future.get();
        }

请问

this->postProcessParall(block_start, height-block_start, height, width, scale_idx, postThres, origin_output, &bboxes);

这一步是有什么用吗？
这一步之前提交多线程操作
这一步之后运行多线程操作
这一步没看懂有什么用