Read rst gstreamer with nvidia acceleration

i try to use gstreamer to read rstp without latency as below:

import cv2

url = "rtsp://admin:abcd1234@"
pipeline = 'rtspsrc location=%s latency=0 ! decodebin ! ' % url

cvt_pipeline = (
                'videoscale ! '
                'video/x-raw, width=(int)%d, height=(int)%d !'
                'videoconvert ! appsink sync=false'
                % (1920, 1080)
cap = cv2.VideoCapture(pipeline + cvt_pipeline, cv2.CAP_GSTREAMER)

while True:
      ret,frame =
      if not ret:
        print('empty frame')

it is work, but it use cpu too much.
i find out that, i can use gstreamer with nvcodec. (Install NVDEC and NVENC as GStreamer plugins · GitHub)
but don’t know how to implement it. Could you guide me to do it?

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• 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 github link you posted has nothing to do with Nvidia. You may need to refer the original author. And the gstreamer plugin mentioned in the github is not provided by Nvidia but by other 3rd party. Please refer to the original author too. sys/nvdec/gstnvdec.c · 1.14 · GStreamer / gst-plugins-bad · GitLab