Multiple gpu in deepstream 6.0

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)- GPU (RTX3060) Dual graphic card
• DeepStream Version -6.0
• TensorRT Version -
• NVIDIA GPU Driver Version (valid for GPU only)-470


I am running deepstream python sample app test 3 on multiple gpu (2 gpu present in my system). I already changed in pgie config ( gpu-id=1 ) and run test-3 then in stream detection (bounding box) not showing. Nothing has changed in sample apps and pgie except (gpu-id).
Any help would be appricated. Thanks in advance.

try to change the tracker config file

Did you enable osd?

No only made changes for gpu-id in pgie. Rest is same as deepstream sample test-3 (python)

Please set input source cudadec-memtype=2 // Memory type Unified
osd streammux nvinfer nvbuf-memory-type=3 // Allocate Unified cuda memory in the python app and try again.
I tried it using deepstream-app, i used file sink, it works.

There is no update from you for a period, assuming this is not an issue anymore.
Hence we are closing this topic. If need further support, please open a new one.

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