The same FPS for all different YOLOv8 models (n, s, m, l, x) when converting to and running with TensorRT

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

we are getting same FPS for all the models we converted pt to onnx model but face issues with converting into tensorRT but there are no errors .

image (7)
image (7)878×991 17.3 KB

Here, as you can see, I am getting this for all the models for yolov8n_320/640, yolov8m_320/640, yolov8s_320/640, yolov8l_320/640, yolov8x_320/640.

3

Please provide complete information as applicable to your setup. Thanks
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)

4

image (1)
image (1)1366×768 101 KB

As you can see here:

image
image1217×642 87.3 KB

These are the multiple streams that I have been using for my building my app image|690x363

5

Since you are using rtsp source, the FPS are limited by your source. Even you are using different YOLOv8 models, the FPS are pretty much the same.

1 Like