Deepstream Compatibility

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

**• Hardware Platform (Jetson / GPU) dGPU
**• DeepStream Version 6.1
• TensorRT Version 8.2.4
**• NVIDIA GPU Driver Version (valid for GPU only)**vNVIDIA GeForce RTX 4070 535.171.04 (CUDA 12.2)
• Issue Type( questions, new requirements, bugs) Compatibility

(Also) CUDA Runtime (11.6)
cuDNN (8.4.0)

I am installing DeepStream without a container, because i am trying to implement it in my own image (which has the TensorRT Version, the cuda runtime and the cuDNN mentioned before), following the instructions :
https://docs.nvidia.com/metropolis/deepstream/6.1/dev-guide/text/DS_Quickstart.html
( I did not change the GOU drivers)

Deepstream 6.1 seemed the best choice, as shown in compatibility matrix in the link, but it still crushes (i think due to an old TensorRT version), while trying to deserialize the .
What do you suggest me to do given my current setup?

>  WARN    nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Warning 
>  fromNvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1888> [UID = 1]: deserialize engine from file :/workspaces/lambda/python/video/deepstream/configs/vis-tiny-latest.reparam.onnx failed
> 0:00:00.544912029 66449 0x56d7d1535a70 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1993> [UID = 1]: deserialize backend context from engine from file/vis-tiny-latest.reparam.onnx failed, try rebuild
> 0:00:00.544917191 66449 0x56d7d1535a70 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files
> ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:860 failed to build network since there is no model file matched.
> ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:799 failed to build network.
> 0:00:00.707583120 66449 0x56d7d1535a70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1934> [UID = 1]: build engine file failed
> 0:00:00.707903119 66449 0x56d7d1535a70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2020> [UID = 1]: build backend context failed
> 0:00:00.707908625 66449 0x56d7d1535a70 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1257> [UID = 1]: generate backend failed, check config file settings
> 0:00:00.707917235 66449 0x56d7d1535a70 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<nvinfer0> error: Failed to create NvDsInferContext instance
> 0:00:00.707919103 66449 0x56d7d1535a70 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<nvinfer0> error: Config file path: /config_infer_primary.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
> ERROR: Pipeline doesn't want to pause.
> ERROR: from element /GstPipeline:pipeline0/GstNvInfer:nvinfer0: Failed to create NvDsInferContext instance
3

If you want to build your own image, please refer to this project.

It is not recommended to use DS-6.1 to avoid some problems that have been fixed.

Here is the compatibility table.

https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Installation.html#id9

4

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

5

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