데이터셋을 올바르게 분할하기

import random
from pathlib import Path

images = sorted(Path("datasets/practice/images").glob("*.jpg"))
random.Random(0).shuffle(images)
train, val = images[:90], images[90:109]  # a random per-image 70/15 split

def group(image):
    return image.stem.rsplit("_", 1)[0]

shared = {group(p) for p in train} & {group(p) for p in val}
print(f"{len(shared)} of {len({group(p) for p in val})} val groups also appear in train")

13 of 13 val groups also appear in train

import random
from collections import Counter, defaultdict
from pathlib import Path

root = Path("datasets/practice")  # contains images/ and labels/

def group(image):
    return image.stem.rsplit("_", 1)[0]  # "cam2_2026-05-01_000124" -> "cam2_2026-05-01"

groups = defaultdict(list)
for image in sorted((root / "images").glob("*.jpg")):
    groups[group(image)].append(image)

keys = sorted(groups)
random.Random(0).shuffle(keys)  # fixed seed: the same split on every run
total, assigned = sum(len(v) for v in groups.values()), 0
splits = {"train": [], "val": [], "test": []}
for key in keys:  # assign whole groups until each split reaches its 70/15/15 share
    share = assigned / total
    splits["train" if share < 0.70 else "val" if share < 0.85 else "test"] += groups[key]
    assigned += len(groups[key])

counts = {}
for split, images in splits.items():
    (root / f"{split}.txt").write_text("".join(f"./images/{p.name}\n" for p in images))
    labels = [root / "labels" / f"{p.stem}.txt" for p in images]
    counts[split] = Counter(int(r.split()[0]) for f in labels if f.exists() for r in f.read_text().splitlines() if r.strip())

all_classes = set().union(*counts.values())
for split, images in splits.items():
    missing = len(all_classes - set(counts[split]))
    print(f"{split:>5}: {len(images):3d} images, {len({group(p) for p in images}):2d} groups, {missing} of {len(all_classes)} classes missing")

train:  90 images, 11 groups, 5 of 71 classes missing
  val:  20 images,  2 groups, 36 of 71 classes missing
 test:  18 images,  3 groups, 41 of 71 classes missing

path: ./datasets/forklift
train: images/train
val:
  - images/val_curated      # stable, your regression suite
  - images/val_production   # rotates with newly collected frames
test: images/test

from ultralytics import YOLO

model = YOLO("runs/detect/train/weights/best.pt")  # your fine-tuned checkpoint
for data in ("val_curated.yaml", "val_production.yaml"):
    metrics = model.val(data=data)
    print(f"{data:<20} mAP50-95={metrics.box.map:.3f}")