DeepStream python apps stopped working

• Hardware Platform (Jetson / GPU) Orin AGX
• DeepStream Version 6.1.1
• JetPack Version (valid for Jetson only) 5.0.2
• TensorRT Version 8.4.1.5

• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

I have recently installed DeepStream 6.1.1 with python bindings. After install I tried several of the sample python apps and all worked well.

I have done a lot of tests, some with my own custom pipelines, without any issues until yesterday.

Today, out of the blue, DeepStream stopped working! For example, when I try to run deepstream-test1 app located in

/opt/nvidia/deepstream/deepstream/sources/deepstream_python_apps/apps

using:

$ python deepstream_test_1.py sample_720p.h264

I get the following error:

0:00:50.685985376 8300 0x1a5f2920 WARN nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1950> [UID = 1]: failed to serialize cude engine to file: /opt/nvidia/deepstream/deepstream-6.1/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
INFO: [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x368x640
1 OUTPUT kFLOAT conv2d_bbox 16x23x40
2 OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40

nvbufsurface: Failed to create EGLImage.
0:00:50.873619744 8300 0x1a5f2920 WARN nvinfer gstnvinfer.cpp:943:gst_nvinfer_start: error: Failed to set buffer pool to active
Error: gst-resource-error-quark: Failed to set buffer pool to active (1): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(943): gst_nvinfer_start (): /GstPipeline:pipeline0/GstNvInfer:primary-inference

Did the tests include nveglglessink?

Yes, it was always there.

He had an Orin AGX dev kit, we installed JetPack 5.0.2. After a week or so DeepStream 6.1.1 was released, so we installed this as well along with python bindings.

I tested several python test apps, e.g. deepstream-test1, deepstream-test4, deepstream-imagedata-multistream, all of the worked with osd, egl plugins.

I am connecting remotely to the devkit using NoMachine.

All issues begun after we changed the IP of the devkit. We didn’t change anything else, just the IP.

Does deepstream-test4 still work with the --no-display option?

After connecting a normal display to the device the problem went away. Thank you all for your support!