Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU) :RTX2080TI• DeepStream Version :5.0• JetPack Version (valid for Jetson only) • TensorRT Version :TensorRT-7.0.0.11• NVIDIA GPU Driver Version (valid for GPU only) :Driver Version: 440.82 CUDA Version: 10.2• Issue Type( questions, new requirements, bugs) :questions• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing) • Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
I can build the YOLOV3 plugin in the folder /opt/nvidia/deepstream/deepstream/sources/objectDetector_Yolo
and run it well.
However, when I tried to printf/std::cout some variables to understand the work flow of DeepStream, nothing was displayed in the console.
the code is as following:
static bool getYoloNetworkInfo (NetworkInfo &networkInfo, const NvDsInferContextInitParams* initParams)
std::cout << "#############################" << std::endl;
std::string yoloCfg = initParams->customNetworkConfigFilePath;
std::string yoloType;
But when the deepstream-app -c deepstream_app_config_yoloV3.txt return as a failure, the debug information was displayed in the console.
So strange and why?
Anybody can help?
mchi
June 8, 2021, 12:47am
4
did a quick test with below change and run commands below, it can print out the “##…#”.
# make -C nvdsinfer_custom_impl_Yolo
# deepstream-app -c deepstream_app_config_yoloV3_tiny.txt
root@f98fe2c6c449:/opt/nvidia/deepstream/deepstream-5.1/sources/objectDetector_Yolo# cd -
/opt/nvidia/deepstream/deepstream-5.1/sources/objectDetector_Yolo/nvdsinfer_custom_impl_Yolo
root@f98fe2c6c449:/opt/nvidia/deepstream/deepstream-5.1/sources/objectDetector_Yolo/nvdsinfer_custom_impl_Yolo# git diff
diff --git a/nvdsparsebbox_Yolo.cpp b/nvdsparsebbox_Yolo.cpp
index 17f47ee..64327ae 100644
--- a/nvdsparsebbox_Yolo.cpp
+++ b/nvdsparsebbox_Yolo.cpp
@@ -303,6 +303,8 @@ extern "C" bool NvDsInferParseCustomYoloV3Tiny(
//{0, 1, 2}}; // as per output result, select {1,2,3}
{1, 2, 3}};
+ std::cout << "#############################" << std::endl;
+
return NvDsInferParseYoloV3 (
outputLayersInfo, networkInfo, detectionParams, objectList,
kANCHORS, kMASKS);
Thank you very much for your reply.
Can you add the test code in nvdsinfer_yolo_engine.cpp.
the function is
static bool getYoloNetworkInfo (NetworkInfo &networkInfo, const NvDsInferContextInitParams* initParams)
like this:
static bool getYoloNetworkInfo (NetworkInfo &networkInfo, const NvDsInferContextInitParams* initParams)
std::cout << "#############################" << std::endl;
std::string yoloCfg = initParams->customNetworkConfigFilePath;
std::string yoloType;
std::transform (yoloCfg.begin(), yoloCfg.end(), yoloCfg.begin(), [] (uint8_t c) {
return std::tolower (c);});
…
mchi
June 8, 2021, 1:42am
6
did you update the lib used by DS after modification and generating the lib?
Yes, I update the libnvdsinfer_custom_impl_Yolo.so
-rwxr-xr-x 1 root root 754840 6月 8 09:53 /opt/nvidia/deepstream/deepstream-5.0/lib/libnvdsinfer_custom_impl_Yolo.so*
Can you just make a simple test.
If you can print the #############################
I will solve the problem myself.
Thank you
mchi
June 8, 2021, 2:22am
8
diff --git a/nvdsinfer_yolo_engine.cpp b/nvdsinfer_yolo_engine.cpp
index 1a70baf..1b39243 100644
--- a/nvdsinfer_yolo_engine.cpp
+++ b/nvdsinfer_yolo_engine.cpp
@@ -34,6 +34,8 @@ static bool getYoloNetworkInfo (NetworkInfo &networkInfo, const NvDsInferContext
std::string yoloCfg = initParams->customNetworkConfigFilePath;
std::string yoloType;
+ std::cout << "########## ********** ###########" << std::endl;
+
std::transform (yoloCfg.begin(), yoloCfg.end(), yoloCfg.begin(), [] (uint8_t c) {
return std::tolower (c);});
1 Like
Thank you , I will check my problem
