How can nvinfer with darknet recog image in video buffer and recog a image alone at the same pipeline

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU)**TX2
• DeepStream Version 4.0.2
• JetPack Version (valid for Jetson only)
• TensorRT Version 5.1.6
• NVIDIA GPU Driver Version (valid for GPU only)

i have to package nvinfer as function, which is used to recog image and video, how can i make the pipeline

3

@yl920182704

I think following samples should be helpful for you to run

/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream-test1
/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream-test2

But you have to convert DarkNet model into TensorRT engine by yourself with handwriting usage of TensorRT C++ APIs.
You can refer to DarkNet-to-TensorRT conversions under /opt/nvidia/deepstream/deepstream-5.0/sources/objectDetector_Yolo/.