Difference output when using Deepstream pipeline on difference GPU cards

Please provide complete information as applicable to your setup.

• Hardware Platform (GPU)
• DeepStream Version: 6.0
• TensorRT Version 8.0.1
• NVIDIA GPU Driver Version (valid for GPU only): Driver Version: 470.103.01
• Issue Type( questions, new requirements, bugs): questions
• 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)

I have used the same below gst pipeline to test on differece machine.

		! nvinfer config-file-path="./config_engine.txt" ! nvvideoconvert ! nvdsosd \
		! nvvideoconvert ! videoconvert ! jpegenc ! jpegparse ! multifilesink location="$(basename $filename)"

And the other application read image and parse data into TensorRT engine inference.
The application always have the same results on difference machines T4, GTX 1080 and 3060

But with above gst pipeline. I got the difference result of the difference machine. The first time I think it was about architechture of hardware will affect to output but the application.

Could anyone help me suggest what will be consider the reason cause difference output from the gst deepstream pipeline?

I’m closing this topic due to there is no update from you for a period, assuming this issue was resolved.
If still need the support, please open a new topic. Thanks

What kind of difference? Is the difference visible?

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.