Deepstream 3d action

Can you please guide me on how can I proceed to use the DS_3D_Action app(DeepStream 3D Action Recognition App — DeepStream 6.1.1 Release documentation) in python deep stream(deepstream_python_apps/apps at master · NVIDIA-AI-IOT/deepstream_python_apps · GitHub) with nvinferserver. I have tried to integrate the nvdspreprocess with the python deepstream but ended with the following error.

features= <Gst.CapsFeatures object at 0x7f3b1e683c40 (GstCapsFeatures at 0x7f3a3400c8c0)>
0:00:00.709075668   901 0x7f3a34069230 WARN           nvinferserver gstnvinferserver.cpp:506:gst_nvinfer_server_push_buffer:<primary-inference> error: Internal data stream error.
0:00:00.709111215   901 0x7f3a34069230 WARN           nvinferserver gstnvinferserver.cpp:506:gst_nvinfer_server_push_buffer:<primary-inference> error: streaming stopped, reason not-linked (-1)
Error: gst-stream-error-quark: Internal data stream error. (1): gstnvinferserver.cpp(506): gst_nvinfer_server_push_buffer (): /GstPipeline:pipeline0/GstNvInferServer:primary-inference:
streaming stopped, reason not-linked (-1)
Exiting app

sequence_image_process.cpp:586, [INFO: CUSTOM_LIB] SequenceImagePreprocess is deinitializing

I have created the triton server which is accepting the temporal batch so I need to pass temporal batch from python deepstream app to call the server.

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU NVIDIAT4
• DeepStream Version 6.0
• NVIDIA GPU Driver Version (valid for GPU only) NVIDIA T4 cuda 11.4

Hi @kumarrajwani1811 , Could you provide your code that can run in the T4 env? Thanks

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

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