Some samples from tao_others doesn't work on Nvidia Jetson AGX Orin 32 GB (dev kit)

Some samples from tao_others doesn’t work on Nvidia Jetson AGX Orin 32 GB (dev kit) after firmware update to 4 GB version emulation mode (Jetson Orin Nano 4 GB).

Steps to reproduce:

  1. git clone GitHub - NVIDIA-AI-IOT/deepstream_tao_apps: Sample apps to demonstrate how to deploy models trained with TAO on DeepStream

  2. launch apps/tao_detection samples
    for example, ./apps/tao_detection/ds-tao-detection -c configs/TrafficCamNet/traffic_cam_config.txt -i file:////home/dev/projects/deepstream_tao_apps/1.MOV

It doesn’t work by default but launches after replacement to codec x264enc
enc = gst_element_factory_make (“nvv4l2h264enc”, “h264-enc”);
enc = gst_element_factory_make (“x264enc”, “h264-enc”);

  1. replace codec to x264 and launch sample from tao_other - get an error
    ./deepstream-faciallandmark-app 1 …/…/…/configs/facial_tao/sample_faciallandmarks_config.txt file:////home/dev/projects/deepstream_tao_apps/gaze.mp4 …/…/…/faciallandmark

dev@dev-desktop:~/projects/deepstream_tao_apps/apps/tao_others/deepstream-faciallandmark-app$ ./deepstream-faciallandmark-app 1 …/…/…/configs/facial_tao/sample_faciallandmarks_config.txt file:////home/dev/projects/deepstream_tao_apps/gaze.mp4 …/…/…/faciallandmark
Request sink_0 pad from streammux
OSD and sink elements link failure.

What is the error log when you run by default?

It doesn’t work by default but launches after replacement to codec x264enc
enc = gst_element_factory_make (“nvv4l2h264enc”, “h264-enc”);
enc = gst_element_factory_make (“x264enc”, “h264-enc”);

It means that an error “codec was not found” occured on launch, so we changed codec to x264enc.
But when we launch tao_others samples with x264enc codec we get another error "OSD and sink elements link failure. "

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

It should work by default. Also, you mention that it happens after firmware update to 4 GB version emulation mode. I assume that it was working before firmware update.
Suggest you use an l4t deepstream docker to test inside it again.
If you still meet error again, please create forum topic in deepstream forum instead to get further help.

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