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
- fdl.yml (opens in a new tab)text/yaml
OSCAR Service Definition
Show content of fdl.yml
- script.sh (opens in a new tab)text/x-shellscript
OSCAR Service Script
Show content of script.sh
- icon.png (opens in a new tab)image/png
OSCAR Service Icon
Show content of icon.png
- input.png (opens in a new tab)image/png
Sample detection image — Replace with a representative image for running the YOLOv8 detector.
Show content of input.png
- Expected detection outputExpected artifactimage/png
Expected detection output — PNG image produced by the service containing annotated detections.
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.
Upload the sample detection image to the service storage.
oscar-cli service put-file yolov8 {source}Wait for the remote inference to produce detection outputs.
Time required: PT60SDownload 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
- application/json
Show content of ro-crate-metadata.json