# YOLO Plugin Error **URL:** \ **Category:** DeepStream SDK\ **Created:** [October 17, 2018, 8:07am UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295 "2018-10-17T08:07:09Z")\ **Posts on this page:** 18\ **Page:** 1
**Author:** ![qweasdzxc](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@qweasdzxc](https://forums.developer.nvidia.com/u/qweasdzxc)\ **Post date:** [October 17, 2018, 8:07am UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/1 "2018-10-17T08:07:09Z")
Hi There I am trying [https://github.com/vat-nvidia/deepstream-plugins](https://github.com/vat-nvidia/deepstream-plugins) for YOLO v3 plugins. I am getting following error when trying to run make command from ~/yolo-plugin/deepstream-plugins/sources/plugins/gst-yoloplugin-tesla$ Error is Makefile:34: \*\*\* “CUDA\_VER variable is not set in Makefile.config”. Stop. please suggest ---
**Author:** ![Amycao](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/amycao/32/11342_2.png) [@Amycao](https://forums.developer.nvidia.com/u/Amycao)\ **Post date:** [October 17, 2018, 8:17am UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/2 "2018-10-17T08:17:57Z")
Please modify all the variables in Makefile.config under the plugin dir. a clip for reference CUDA\_VER:= 9.2 #Set to TEGRA for jetson or TESLA for dGPU’s PLATFORM:= TESLA #For Tesla Plugins OPENCV\_INSTALL\_DIR:= /home/tse/cuse/opencv3.4/opencv-3.4.0/install TENSORRT\_INSTALL\_DIR:= /home/tse/cuse/trt4.0.1.6/usr DEEPSTREAM\_INSTALL\_DIR:= /home/tse/work/deepstream/DeepStream\_Release #CUDNN\_DIR := /home/tse/work/cpxavier/cudnn7.3.0.23/cuda ---
**Author:** ![qweasdzxc](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@qweasdzxc](https://forums.developer.nvidia.com/u/qweasdzxc)\ **Post date:** [October 17, 2018, 8:57am UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/3 "2018-10-17T08:57:30Z")
Thanks I have given path here CUDA\_VER:= 9.2 instead of only version thanks a lot ---
**Author:** ![qweasdzxc](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@qweasdzxc](https://forums.developer.nvidia.com/u/qweasdzxc)\ **Post date:** [October 17, 2018, 9:14am UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/4 "2018-10-17T09:14:20Z")
Hi I am getting another error File does not exist : data/yolov3-tiny.cfg trt-yolo-app: yolo.cpp:135: void Yolo::createYOLOEngine(int, std::\_\_cxx11::string, std::\_\_cxx11::string, std::\_\_cxx11::string, nvinfer1::DataType, Int8EntropyCalibrator\*): Assertion `fileExists(yoloConfigPath)’ failed. Aborted (core dumped) Although I have yolov3-tiny.cfg inside data ---
**Author:** ![Amycao](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/amycao/32/11342_2.png) [@Amycao](https://forums.developer.nvidia.com/u/Amycao)\ **Post date:** [October 17, 2018, 9:51am UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/5 "2018-10-17T09:51:36Z")
in this file sources/lib/network\_config.h, by default, it all comment out, please uncomment one which you are using // Uncomment the macro to choose a type of network #define MODEL\_V2 yoloV2 // #define MODEL\_V2\_TINY // #define MODEL\_V3 //#define MODEL\_V3\_TINY ---
**Author:** ![qweasdzxc](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@qweasdzxc](https://forums.developer.nvidia.com/u/qweasdzxc)\ **Post date:** [October 17, 2018, 9:59am UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/6 "2018-10-17T09:59:47Z")
Hi, I have already done that ---
**Author:** ![qweasdzxc](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@qweasdzxc](https://forums.developer.nvidia.com/u/qweasdzxc)\ **Post date:** [October 17, 2018, 10:04am UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/7 "2018-10-17T10:04:56Z")
Even after running sudo make reinstall it’s giving error ---
**Author:** ![qweasdzxc](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@qweasdzxc](https://forums.developer.nvidia.com/u/qweasdzxc)\ **Post date:** [October 17, 2018, 11:17am UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/8 "2018-10-17T11:17:59Z")
Changes done is below Added path for video url in deepstream-app\_yolo\_config.txt [source0] enable=1 #Type - 1=CameraV4L2 2=URI 3=MultiURI type=3 uri=file://home/nvidia/yolo-plugin/deepstream-plugins/sources/apps/deepstream-yolo/sample\_720p.mp4 I am getting below error nvidia@nvidia-HP-Z440-Workstation:~/yolo-plugin/deepstream-plugins/sources/apps/deepstream-yolo$ ./deepstream-yolo-app sample\_720p.h264 Now playing: sample\_720p.h264 File does not exist : sources/lib/models/yolov3-tiny-kFLOAT-batch1.engine Unable to find cached TensorRT engine for network : yolov3-tiny precision : kFLOAT and batch size :1 Creating a new TensorRT Engine File does not exist : data/yolov3-tiny.cfg deepstream-yolo-app: yolo.cpp:135: void Yolo::createYOLOEngine(int, std::\_\_cxx11::string, std::\_\_cxx11::string, std::\_\_cxx11::string, nvinfer1::DataType, Int8EntropyCalibrator\*): Assertion `fileExists(yoloConfigPath)’ failed. Aborted (core dumped) ---
**Author:** ![qweasdzxc](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@qweasdzxc](https://forums.developer.nvidia.com/u/qweasdzxc)\ **Post date:** [October 17, 2018, 12:15pm UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/9 "2018-10-17T12:15:25Z")
> [@](#): > > Also I thought to clean make file and run make again and see what happens. So I followed below commands > > make clean > make > sudo make install > > And I am getting below error > > Building deepstream-yolo-app > g++ -o deepstream-yolo-app deepstream-yolo-app.o -I /home/nvidia/Downloads/DeepStream\_Release/sources/includes -I /usr/include/gstreamer-1.0 -std=c++11 -Wunused-variable -Wfatal-errors `pkg-config --cflags gstreamer-1.0` `pkg-config --libs gstreamer-1.0` > Installing deepstream-yolo-app > cp -rv deepstream-yolo-app /usr/bin/ > ‘deepstream-yolo-app’ → ‘/usr/bin/deepstream-yolo-app’ > cp: cannot create regular file ‘/usr/bin/deepstream-yolo-app’: Permission denied > Makefile:77: recipe for target ‘install’ failed > make: \*\*\* [install] Error 1 ---
**Author:** ![abramjos](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@abramjos](https://forums.developer.nvidia.com/u/abramjos)\ **Post date:** [October 17, 2018, 1:49pm UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/10 "2018-10-17T13:49:11Z")
Hi Deepshikha, provide absolute paths in network-config.cpp. It will help. Its pretty much messed up. all are working for us ```auto const std::string kDS_LIB_PATH = "/path-to-yolo_plugin/deepstream-plugins/sources/lib/"; const std::string kMODELS_PATH = kDS_LIB_PATH+"models/"; const std::string kDETECTION_RESULTS_PATH ="/path-to-yolo_plugin/deepstream-plugins/data/detections/"; const std::string kCALIBRATION_SET = "/path-to-yolo_plugin/deepstream-plugins/data/calibration_images.txt"; const std::string kTEST_IMAGES = "/path-to-yolo_plugin/deepstream-plugins/data/test_images.txt"; ..................................................... #ifdef MODEL_V3_TINY // Model V3 Tiny specific common global vars const float kPROB_THRESH = 0.5f; const float kNMS_THRESH = 0.5f; const std::string kYOLO_CONFIG_PATH = "absolute_path_to/data/yolov3-tiny.cfg"; const std::string kTRAINED_WEIGHTS_PATH = "absolute_path_to/data/yolov3-tiny.weights"; const std::string kNETWORK_TYPE = "yolov3-tiny"; const std::string kCALIB_TABLE_PATH = "absolute_path_to/calibration/yolov3-tiny-calibration.table"; const uint kBBOXES = 3; const std::vector kANCHORS = {10.0, 14.0, 23.0, 27.0, 37.0, 58.0, 81.0, 82.0, 135.0, 169.0, 344.0, 319.0}; #endif ``` ---
**Author:** ![Amycao](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/amycao/32/11342_2.png) [@Amycao](https://forums.developer.nvidia.com/u/Amycao)\ **Post date:** [October 17, 2018, 1:49pm UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/11 "2018-10-17T13:49:24Z")
Update the paths of the .cfg and .weights file and other network params in `net work_config.cpp` file if required. one example for config file, others also need modidy. const std::string kYOLO\_CONFIG\_PATH = “…/…/…/data/yolov2.cfg”; ---
**Author:** ![abramjos](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@abramjos](https://forums.developer.nvidia.com/u/abramjos)\ **Post date:** [October 17, 2018, 1:51pm UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/12 "2018-10-17T13:51:49Z")
> [@](#): > > > [@](#): > > > > Also I thought to clean make file and run make again and see what happens. So I followed below commands > > > > make clean > > make > > sudo make install > > > > And I am getting below error > > > > Building deepstream-yolo-app > > g++ -o deepstream-yolo-app deepstream-yolo-app.o -I /home/nvidia/Downloads/DeepStream\_Release/sources/includes -I /usr/include/gstreamer-1.0 -std=c++11 -Wunused-variable -Wfatal-errors `pkg-config --cflags gstreamer-1.0` `pkg-config --libs gstreamer-1.0` > > Installing deepstream-yolo-app > > cp -rv deepstream-yolo-app /usr/bin/ > > ‘deepstream-yolo-app’ → ‘/usr/bin/deepstream-yolo-app’ > > cp: cannot create regular file ‘/usr/bin/deepstream-yolo-app’: Permission denied > > Makefile:77: recipe for target ‘install’ failed > > make: \*\*\* [install] Error 1 dont use sudo in that case. It should be working ---
**Author:** ![abhosle](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@abhosle](https://forums.developer.nvidia.com/u/abhosle)\ **Post date:** [October 17, 2018, 6:48pm UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/13 "2018-10-17T18:48:46Z")
Hello guys, Do you know if the yolo-plugin works with GTX 1080? Thanks! ---
**Author:** ![abramjos](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@abramjos](https://forums.developer.nvidia.com/u/abramjos)\ **Post date:** [October 18, 2018, 3:48am UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/14 "2018-10-18T03:48:36Z")
Yes it should be. I am using 1080Ti and it is working fine. Apparently, the plugin doesnt has a hardware limitation. ---
**Author:** ![abhosle](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@abhosle](https://forums.developer.nvidia.com/u/abhosle)\ **Post date:** [October 18, 2018, 4:34pm UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/15 "2018-10-18T16:34:49Z")
Thank you! ---
**Author:** ![abhosle](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@abhosle](https://forums.developer.nvidia.com/u/abhosle)\ **Post date:** [October 22, 2018, 6:13pm UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/16 "2018-10-22T18:13:50Z")
While using the yolo plugin, I am using an rtsp stream as my source. However, I am getting this error regarding batchSize: yoloplugin\_lib.cpp:116: YoloPluginCtx\* YoloPluginCtxInit(YoloPluginInitParams\*, size\_t): Assertion `ctx-\>batchSize \> 0’ failed. Aborted (core dumped) Do you know what might be causing this? ---
**Author:** ![skabhilash10](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@skabhilash10](https://forums.developer.nvidia.com/u/skabhilash10)\ **Post date:** [July 18, 2019, 10:23am UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/17 "2019-07-18T10:23:29Z")
> [@](#): > > Yes it should be. I am using 1080Ti and it is working fine. Apparently, the plugin doesnt has a hardware limitation. Hi can you please share the plugin implementation , i am facing issues during implementation ---
**Author:** ![TomNVIDIA](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/tomnvidia/32/14181_2.png) [@TomNVIDIA](https://forums.developer.nvidia.com/u/TomNVIDIA)\ **Post date:** [October 12, 2021, 4:19pm UTC](https://forums.developer.nvidia.com/t/yolo-plugin-error/66295/18 "2021-10-12T16:19:26Z")
Closed on October 12, 2021, 4:19pm UTC