Can i use yolo models between deepstream, such as onnx? Instead of converting an onnx model to a tensorRT model first

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version ds7.1-docker
• JetPack Version (valid for Jetson only)
• TensorRT Version10.3
• NVIDIA GPU Driver Version (valid for GPU only) 560.35
• Issue Type( questions, new requirements, bugs) questions

I want to use a yolo image segmentation model. Can I use a model like pt or onnx directly instead of converting them to a tensorRT model first?

You can refer to our deepstream_tools sample.

Is both object detection and image segmentation applicable in yolov8

For more scenarios, you can refer to this DeepStream-Yolo too.