← Back to catalog

SERVICE DETAILS

YOLOv8 Service (by AI4EOSC)

Asynchronous

Overview

OSCAR service that deploys the YOLOv8 object detection workflow from AI4EOSC.

Deployment requirements

Memory
4 GiB
Processors
2 vCPU0 GPU

Files & artifacts

Usage & acceptance tests

Asynchronous YOLOv8 acceptance test

Upload a sample image, wait for detection to complete remotely, then download the prediction artifact and check the expected confirmation text.

  1. Upload the sample detection image to the service storage.

    oscar-cli service put-file yolov8 {source}
  2. Wait for the remote inference to produce detection outputs.

    Time required: PT60S
  3. Download the most recent output artifact and confirm it is the expected detection PNG.

    oscar-cli service get-file yolov8 --download-latest-into {destination}

RO-Crate metadata