Deepstream Python Apps docker/freezing problem

I’m trying to run ssd_inception_v2_coco sample of deepstream_python_apps repo on a machine with GeForce RTX 2070 GPU, cuda 10.2 and cudnn 7.5.
First, I tried nvcr.io/nvidia/deepstream:5.1-21.02-triton docker as it was required to have deepstream 5.1 and I got Unable to set device in gst_nvstreammux_change_state error.
Then I tried to test v1.0 tag with nvcr.io/nvidia/deepstream:5.0.1-20.09-triton docker and the result was app freezing on the gstreamer main loop run line (after allocating resources and loading model).

Please help me with the proper docker container or a way solving the freezing problem, thanks.

• Hardware Platform (GPU): GeForce RTX 2070
• DeepStream Version: 5.1, 5.0
• NVIDIA GPU Driver Version (valid for GPU only): 440.100
• Issue Type( questions, new requirements, bugs) questions

I see your driver is 440.100, deepstream 5.1 required Driver: R460.32+, please update the driver, and try again.

@amycao Thanks for your response, but as updating the driver effects other applications and may cause conflicts, do you have any suggestion for the freezing problem in v1.0 tag of deepstream_python_apps? I have attached running messages

Hi,
It did not have error, how about run with CUDA_VISIBLE_DEVICES=0 preceding app you run.

Hi,
No, This doesn’t have error but it freezes in this situation and doesn’t do anything. GPU resources are taken and nothing happens.

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

Can you run other samples?