How to get default python app path in deepstrem sdk and run yolo4 model

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson nano board
• DeepStream Version :5.1
• JetPack Version (valid for Jetson only):4.4
• TensorRT Version:no
• NVIDIA GPU Driver Version (valid for GPU only):no idea
• Issue Type( questions, new requirements, bugs)
• 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)

Hi,

It’s open-sourced in the below GitHub:
More, if you are using Deepstream 5.1, it’s recommended to reflash your system to JetPack 4.5.1.

Thanks.

dstest2_tracker_config.txt
bash: dstest2_tracker_config.txt: command not found

opt/nvidia/deepstream/deepstream-5.1/sources/apps/sample_apps/deepstream-test2 its in folder all files present.

fatal error: cuda_runtime_api.h: No such file or directory
#include <cuda_runtime_api.h>

Hi,

You should be able to find cuda_runtime_api.h in the below folder:

/usr/local/cuda-10.2/targets/aarch64-linux/include/cuda_runtime_api.h

Please noted that you need to specify the CUDA version when compiling the Deepstream library.
For example:

$ CUDA_VER=10.2 make

Thanks.

Yolo4 deepstrem run step its give make file compilation error

Please give me step in Jetson nano.

Header file not found

Hi,

You don’t need to build tensorrt_yolov4.
To deploy YoloV4 with Deepstream, please refer to deepstream_yolov4 directly.

If you want to build the TensorRT app, please check the README for the detailed command:

Thanks.