Engine files are absent for deepstream pre-trained models

[user52105]

Aiming to run the deepstream 5.1 with trafficCam pre-trained model have run-time crash. I have noticed that
the sample config file has a link to the model engine file resnet18_trafficcamnet_pruned.etlt_b1_gpu0_int8.engine which is not present among file that is downloaded with trafficCam model TrafficCamNet | NVIDIA NGC. How that file can be obtained?

[mchi]

please provide setip info

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• 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)

[user52105]

Hardware platform GPU - T4
DeepStream Version 5.1
TensorRT 7.2.1
NVIDIA GPU Driver Version 460.32.03 Cuda version 11.2
Issue Type - question
Have DS.5.1 with dependencies as above, download https://catalog.ngc.nvidia.com/orgs/nvidia/models/tlt_trafficcamnet model and run
deepstream-app -c deepstream_app_source1_trafficcamnet.txt see error aiming to download file resnet18_trafficcamnet_pruned.etlt_b1_gpu0_int8.engine.

[mchi]

@user52105

resnet18_trafficcamnet_pruned.etlt_b1_gpu0_int8.engine

https://github.com/NVIDIA-AI-IOT/deepstream_reference_apps/blob/master/deepstream_app_tao_configs/config_infer_primary_trafficcamnet.txt#L30

It’s TensorrRT engine generated by DeepStream based on its TLT model - resnet18_trafficcamnet_pruned.etlt