NVdCF tracker issue with 2 T4

Accelerated Computing Intelligent Video Analytics DeepStream SDK
, ,
1

• Hardware Platform Nvidia Tesla T4
• DeepStream Version 5.1

• TensorRT Version 7.2.2.3
• NVIDIA GPU Driver Version (valid for GPU only) 460.32…03
• Issue Type( questions, new requirements, bugs) question

Hi, while running deepstream with NVDCF tracker with 2 T4 , i am getting the error-
“GPUassert: invalid device ordinal src/modules/NvDCF/NvDCF.cpp 1250”

I had opened the same issue before but for some reason was not able to continue over there.
“NVdCF tracker issue with 2 T4”

Please find the attached config file as asked by @Amycao .

appconfig_x86_full.txt (7.1 KB)

3

Can you repro the issue mentioned with local file?

4

I just tried with local file, with your config, i got the issue. please change gpu-id to same GPU id.

5

yes i can but, i want to offload all my 17 cameras to 2 T4s. So i have to use two gpu-ids.

Is there problem using 2 gpu-id with NvDcF tracker?

6

We do not support it.

7

ok thanks

9

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