Multiple gpu in deepstream 6.0

Accelerated Computing Intelligent Video Analytics DeepStream SDK
#1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)- GPU (RTX3060) Dual graphic card
• DeepStream Version -6.0
• TensorRT Version - 8.2.1.8
• NVIDIA GPU Driver Version (valid for GPU only)-470

Hie,

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.

#3

try to change the tracker config file

#5

Did you enable osd?

#6

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

#7

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.

#9

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.
Thanks