First inference

Run your first inference using copy-paste-ready code.

Estimated read time: 1 minute

Run this first

Don’t worry about the details yet. Just run this to see something work—we’ll explain what it does after.

# Quick start: one image → inference → overlay
from degirum_tools import ModelSpec, remote_assets, Display

model_spec = ModelSpec(
    model_name="yolov8n_coco--640x640_quant_axelera_metis_1",
    zoo_url="degirum/axelera",
    inference_host_address="@local",
    model_properties={"device_type": ["AXELERA/METIS"]},
)
model = model_spec.load_model()

img = remote_assets.three_persons
res = model(img)

with Display("AI Camera") as output_display:
    output_display.show_image(res.image_overlay)

You should see an image with object detections overlayed:

Three people at a crosswalk labeled person.

What just happened

• You specified a model (name and source)

• Loaded it into an inference runtime

• Ran inference on a test image

• Displayed the output using image_overlay