tools/YOLOv8-with-TensorRT-Nvidia-Triton-Server/

[utterances-bot]

YOLOv8 with TensorRT & Nvidia Triton Server | VISION HONG

Intro

https://visionhong.github.io/tools/YOLOv8-with-TensorRT-Nvidia-Triton-Server/

[tofulim]

좋은 글 감사합니다~

[tofulim]

그리고 ultralytics에서 지원해줘서요. 그냥 triton inference server url을 model명으로 넣어줘도 동작합니다.

from ultralytics import YOLO

# Load the Triton Server model
model = YOLO("http://localhost:8000/yolo", task="detect")

# Run inference on the server
results = model("path/to/image.jpg")

• 출처: https://docs.ultralytics.com/guides/triton-inference-server/#why-should-i-export-my-yolov8-model-to-onnx-format-before-using-triton-inference-server