スマートアノテーションと一括ラベリング

from pathlib import Path

import torch

from ultralytics import YOLO
from ultralytics.data.utils import check_det_dataset
from ultralytics.utils.metrics import box_iou
from ultralytics.utils.ops import xywhn2xyxy

data = check_det_dataset("coco128.yaml")  # 128 labeled images, downloaded on first use
images = sorted(Path(data["train"]).glob("*.jpg"))
results = YOLO("yolo26n.pt").predict(images, conf=0.05, verbose=False)  # your labeling model

def review_work(result, image, conf):
    """Return (kept, delete, draw): correct pre-labels, false positives to delete, missed objects to draw."""
    label = Path(str(image).replace("images", "labels")).with_suffix(".txt")
    lines = label.read_text().splitlines() if label.exists() else []  # no label file = background image
    gt = torch.tensor([[float(x) for x in line.split()] for line in lines]).reshape(-1, 5)
    h, w = result.orig_shape
    gt_boxes, gt_cls = xywhn2xyxy(gt[:, 1:], w=w, h=h), gt[:, 0]
    boxes = result.boxes[result.boxes.conf >= conf]
    iou = box_iou(boxes.xyxy, gt_boxes) * (boxes.cls[:, None] == gt_cls[None])  # IoU with same-class boxes only
    matched = set()
    for row in iou:  # greedily match each prediction to its best unmatched ground-truth box
        for j in row.argsort(descending=True).tolist():
            if row[j] >= 0.5 and j not in matched:
                matched.add(j)
                break
    return len(matched), len(boxes) - len(matched), len(gt) - len(matched)

print("conf  kept  delete  draw  edits/image")
for conf in (0.1, 0.25, 0.4, 0.5, 0.7):
    kept, delete, draw = (sum(t) for t in zip(*(review_work(r, i, conf) for r, i in zip(results, images))))
    print(f"{conf:<5} {kept:>4} {delete:>7} {draw:>5} {(delete + draw) / len(images):>12.1f}")

conf  kept  delete  draw  edits/image
0.1    590     490   339          6.5
0.25   468     138   461          4.7
0.4    386      58   543          4.7
0.5    328      35   601          5.0
0.7    230       6   699          5.5