Box

pf.annotate.box draws the outline of each detection's box. It is the quickest way to check what a model found, and the base most other marks are drawn on.

Python
import pixelflow as pf
from mayaku import from_pretrained

predictor = from_pretrained("mayaku-n-det")
result = predictor("street.jpg")
detections = pf.from_mayaku(result, labels=predictor.class_names)
detections = detections.filter_by_confidence(0.5)

image = pf.read_image("street.jpg")
image = pf.annotate.box(image, detections)
pf.save_image("street-boxes.jpg", image)

Box outlines around the people, motorcycles and an umbrella in a street photo

Boxes show what was found, not what it is: add labels for the class and confidence.

Parameters

Parameter Default
image RGB image, drawn on in place
detections the Detections to draw
thickness from the image size line width in pixels: 4 on a 1920×1280 image
colors the default palette list of RGB colors, picked by class_id (see colors)