데이터셋 사양 정의하기

from collections import Counter
from pathlib import Path

from ultralytics.data.utils import IMG_FORMATS, check_det_dataset, img2label_paths

IMAGES_PER_CLASS, INSTANCES_PER_CLASS = 1500, 10_000  # Ultralytics production targets

data = check_det_dataset("coco128.yaml")  # downloads COCO128 (~7 MB) on first run; swap in your data YAML
images = [p for p in Path(data["train"]).rglob("*.*") if p.suffix[1:].lower() in IMG_FORMATS]
image_count, instance_count, background = Counter(), Counter(), 0
for label in map(Path, img2label_paths([str(p) for p in images])):
    classes = [int(r.split()[0]) for r in label.read_text().splitlines() if r.strip()] if label.exists() else []
    instance_count.update(classes)
    image_count.update(set(classes))
    background += not classes

print(f"{len(images)} images, {background} background ({background / len(images):.0%}, target 0-10%)")
print(f"{'class':>12} {'images':>7} {'instances':>10} {'of target':>10}")
ranked = instance_count.most_common()
for cls, n in ranked[:3] + ranked[-3:]:  # best and worst covered classes
    coverage = min(image_count[cls] / IMAGES_PER_CLASS, n / INSTANCES_PER_CLASS)
    print(f"{data['names'][cls]:>12} {image_count[cls]:>7} {n:>10} {coverage:>10.1%}")

never_labeled = [name for i, name in data["names"].items() if i not in instance_count]
print(f"{len(never_labeled)} classes in names with zero labels: {never_labeled[:4]} ...")

128 images, 2 background (2%, target 0-10%)
       class  images  instances  of target
      person      61        254       2.5%
         car      12         46       0.5%
         cup      10         36       0.4%
        bear       1          1       0.0%
      banana       1          1       0.0%
        skis       1          1       0.0%
9 classes in names with zero labels: ['fire hydrant', 'parking meter', 'sheep', 'cow'] ...