NvDsInferCudaEngineGetFromTltModel: TLT encoded model file path not provided

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
GPU
• DeepStream Version
5.0
• JetPack Version (valid for Jetson only)
• TensorRT Version
7.1
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• 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)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

        /* TLT model. Use NvDsInferCudaEngineGetFromTltModel function
         * provided by nvdsinferutils. */
        cudaEngineGetFcn = NvDsInferCudaEngineGetFromTltModel;
        modelPath = safeStr(initParams.tltEncodedModelFilePath);
        dsInferError("modelPath===》");
        dsInferError(modelPath.c_str());

I have printed the absolute model path, and checked everything is ok. But it raised always this error. I think this function NvDsInferCudaEngineGetFromTltModel is supposed to be non-opened in nvdsinferutils.

what should be the reasons for that?

PS: When I installed deepstream on another pc, the same source code, and this error no more showed.

3

Do you mean the modelPath is wrong? Can you reinstall deepstream in your device? Quickstart Guide — DeepStream 6.3 Release documentation

4

the printed modelpath is correct, which could be found with ls command. I reinstalled deepstream and fixed this issue. But I am wondering, how could this error be raised, what the reasons. because This error message cannot be found in deepstream open-source code.

5

What error message?

6

ERROR msg: NvDsInferCudaEngineGetFromTltModel: TLT encoded model file path not provided

7

It may be something missing.