Can't run DeepStream example

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

Hi everyone,

I’m new to NVIDIA DeepStream and am trying to get started by running the example app. However, I’m encountering several issues, and I’m unsure how to proceed.

deepstream-app -c /opt/nvidia/deepstream/deepstream-7.1/samples/configs/deepstream-app/source30_1080p_dec_infer-resnet_tiled_display_int8.txt

Setting min object dimensions as 16x16 instead of 1x1 to support VIC compute mode.
WARNING: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-7.1/samples/configs/deepstream-app/../../models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b30_gpu0_int8.engine open error
0:00:00.206619725 51130 0xaaaae43016f0 WARN                 nvinfer gstnvinfer.cpp:681:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2080> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-7.1/samples/configs/deepstream-app/../../models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b30_gpu0_int8.engine failed
0:00:00.206684489 51130 0xaaaae43016f0 WARN                 nvinfer gstnvinfer.cpp:681:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2185> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-7.1/samples/configs/deepstream-app/../../models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b30_gpu0_int8.engine failed, try rebuild
0:00:00.206704040 51130 0xaaaae43016f0 INFO                 nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2106> [UID = 1]: Trying to create engine from model files
WARNING: [TRT]: DLA requests all profiles have same min, max, and opt value. All dla layers are falling back to GPU

after that it just do nothing.

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
Jetson AGX Orin DevKit
• DeepStream Version
7.1
• JetPack Version (valid for Jetson only)
6.1
• TensorRT Version
10.7.0.23-1+cuda12.6
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
Bug/Question
• 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)
Just run it 🤷🏻‍♂️
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

3
  1. For DS-7.1, it works on TRT 10.3, we have not tested it on TRT 10.7.

https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Installation.html#platform-and-os-compatibility

Building an engine file with a batch-size of 30 will take a lot of time.
Try source2_1080p_dec_infer-resnet_demux_int8.txt, or wait for the engine to be built successfully.

I suggest you try test1 first

cd /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-test1/
make CUDA_VER=12.6
./deepstream-test1-app /opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.h264
4

Thank you for your response. I downgraded TensorRT to version 10.3, but the provided example (deepstream-app -c /opt/nvidia/deepstream/deepstream-7.1/samples/configs/deepstream-app/source30_1080p_dec_infer-resnet_tiled_display_int8.txt) still doesn’t work. The example (from this guide) shows the following warning:

WARNING: [TRT]: DLA requests all profiles have the same min, max, and opt value. All DLA layers are falling back to GPU.

However, the example you provided works fine.

5

Please ignore the warning. deepstream does not use DLA by default

Is there any error output?

If it doesn’t work, it’s probably because Jetpack is not installed correctly. Please use SDKManager to re-burn it.
https://docs.nvidia.com/sdk-manager/install-with-sdkm-jetson/index.html

6

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

7

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