Trt Engine

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

I created trt engine file for custom yolov11 model using this following link:

Ultralytics YOLO11 on NVIDIA Jetson using DeepStream SDK and TensorRT

I was able to create the engine file but how do I test it such that I know that engine file that is made is properly built and the detections are correct?

When I run the deepstream app I do get the fps info but no debug window.

Also, are there any other guide for custom parser as yolo has immense support they already provided one but what about other models?

3

Please refer to this sample.

This example demonstrates how to use a YOLO model as the primary detector to draw bounding boxes onto video frames and save them to a video file.

4

Please provide complete information as applicable to your setup.
• 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)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
• The pipeline being used

5

My issue was solved for the yolo model using the ultralytics method itself thanks for the help, my another question was how to get or create custom parser for other models where they are not provided. Below are my system details

• Hardware Platform (Jetson / GPU) : AGX Orin
• DeepStream Version: 7.1
• JetPack Version (valid for Jetson only): 6.2
• TensorRT Version: 10.3
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs): TRT

• 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): Trying to generate engine file for yolo model and facing issue in getting detection.

• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description): Yolo model, and in general other models

• The pipeline being used: NA

6

The repository above contains the nvdsinfer_custom_impl_Yolo post-processing parsing library, which supports YOLOv11 tensor parsing. You can refer to this example and modify the code according to your model.