Not able to convert "resnet_peoplenet.tlt" model to resnet34_peoplenet_fp16.engine file

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jeston (Orin Nano)
• DeepStream Version 6.2
• JetPack Version (valid for Jetson only) 5.1
• TensorRT Version 8.5.2
• 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)

We are using Jeston Orin Nano, DeepStream SDK 6.2, Jetpack 5.1 and TensorRT 8.5.2

Using the below code

def load_engine(trt_runtime, engine_path):
with open(engine_path, “rb”) as f:
engine_data = f.read()
engine = trt_runtime.deserialize_cuda_engine(engine_data)
return engine

trt_engine_path = “resnet34_peoplenet.tlt”
TRT_LOGGER = trt.Logger(trt.Logger.WARNING)
trt_runtime = trt.Runtime(TRT_LOGGER)
trt_engine = load_engine(trt_runtime, trt_engine_path)

I am getting the error as below
[11/09/2023-16:51:46] [TRT] [E] 1: [stdArchiveReader.cpp::StdArchiveReader::32] Error Code 1: Serialization (Serialization assertion magicTagRead == kMAGIC_TAG failed.Magic tag does not match)
[11/09/2023-16:51:46] [TRT] [E] 4: [runtime.cpp::deserializeCudaEngine::65] Error Code 4: Internal Error (Engine deserialization failed.)

Kindly help on the query

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

resnet34_peoplenet.tlt is not an engine file, it is “elt” model file from TAO toolkit encoded model, you can set it in option “tlt-encoded-model” of nvinfer (together with tlt-model-key).
You may refer to the usage in DeepStream samples.

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