مجموعة بيانات SUN RGB-D للعمق#

# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license

# SUN RGB-D dataset for monocular depth estimation — real indoor, multi-sensor RGB-D (RealSense/Xtion/Kinect), up to ~10 m
# Documentation: https://docs.ultralytics.com/datasets/depth/sunrgbd
# Example usage: yolo depth train data=depth-sunrgbd.yaml model=yolo26n-depth.pt
# parent
# ├── ultralytics
# └── datasets
#     └── depth-sunrgbd  ← downloads here (6.5 GB archive, ~14 GB converted)
#         ├── images/{train,val}  # RGB images
#         └── depth/{train,val}   # paired 16-bit *.png depth maps (images/ -> depth/)
# If an interrupted download leaves a partial dataset, delete the depth-sunrgbd dir and re-run to rebuild it.

path: depth-sunrgbd # dataset root dir (relative to Ultralytics settings 'datasets_dir')
train: images/train # train images (relative to 'path') 9245 images
val: images/val # val images (relative to 'path') 1090 images

nc: 1
names:
  0: depth

channels: 3

# Download script/URL (optional)
download: |
  import random
  import shutil
  from pathlib import Path

  import cv2
  import numpy as np

  from ultralytics.data.utils import save_depth_png
  from ultralytics.utils import TQDM
  from ultralytics.utils.downloads import download

  # Download and extract the official archive (~6.5 GB), then convert each of the 10335 scenes:
  # refined depth_bfx PNGs decode via the SUN RGB-D bit-rotation (d>>3 | d<<13) to millimeters,
  # clipped at 10 m; a deterministic random 1090-scene subset (seed 0) forms the val split
  dir = Path(yaml["path"])  # dataset root dir
  download(["https://rgbd.cs.princeton.edu/data/SUNRGBD.zip"], dir=dir / "source", delete=True, exist_ok=True)
  for split in ("train", "val"):
      (dir / "images" / split).mkdir(parents=True, exist_ok=True)
      (dir / "depth" / split).mkdir(parents=True, exist_ok=True)
  scenes = sorted(p.parent for p in (dir / "source" / "SUNRGBD").rglob("depth_bfx"))
  names = ["_".join(s.relative_to(dir / "source" / "SUNRGBD").parts) for s in scenes]
  val = set(random.Random(0).sample(names, k=1090))
  for scene, name in TQDM(zip(scenes, names), total=len(scenes), desc="Converting"):
      split = "val" if name in val else "train"
      d = cv2.imread(str(next((scene / "depth_bfx").glob("*.png"))), cv2.IMREAD_ANYDEPTH)
      d = (((d >> 3) | (d << 13)) / 1000.0).clip(max=10).astype(np.float32)  # bit-rotated mm -> m
      save_depth_png(dir / "depth" / split / f"{name}.png", d)
      next((scene / "image").glob("*.jpg")).replace(dir / "images" / split / f"{name}.jpg")
  shutil.rmtree(dir / "source")