Why the Primary_Detector resnet10.caffemodel_b1_gpu0_int8.engine does not need a box parser and NMS?

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 5.0
• JetPack Version (valid for Jetson only)
• TensorRT Version 7.0
• NVIDIA GPU Driver Version (valid for GPU only) T4
• 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)

The following command can detect pedestrian and vehicle successfully.

gst-launch-1.0 filesrc location=/opt/nvidia/deepstream/deepstream/sources/Yolov5-in-Deepstream-5.0-master/retinaface/6981450019635268905.mp4 ! qtdemux ! h264parse ! nvv4l2decoder ! m.sink_0 nvstreammux name=m batch-size=1 width=1024 height=560 ! nvinfer config-file-path=/opt/nvidia/deepstream/deepstream-5.0/sources/apps/sample_apps/deepstream-test1/dstest1_pgie_config.txt ! nvvideoconvert ! nvdsosd ! nvvideoconvert ! ‘video/x-raw(memory:NVMM),format=I420’ ! nvv4l2h264enc ! h264parse ! mux.video_0 qtmux name=mux ! filesink location=/tmp/test.mp4

However, why the Yolo detector need a box parser and NMS post-processing?


It depends on the yolov5 model but not deepstream. yolov5/detect.py at master · ultralytics/yolov5 (github.com). Yolov5 is a classifier but not detector. Docker Hub

Yolov5 is not provided by Nvidia. Please refer to yolov5 resources for your questions.

Thanks, I will investgate the source code.

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.