Bộ dữ liệu xView#

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

# DIUx xView 2018 Challenge dataset https://challenge.xviewdataset.org by U.S. National Geospatial-Intelligence Agency (NGA)
# --------  Download and extract data manually to `datasets/xView` before running the train command.  --------
# Documentation: https://docs.ultralytics.com/datasets/detect/xview
# Example usage: yolo train data=xView.yaml
# parent
# ├── ultralytics
# └── datasets
#     └── xView ← downloads here (20.7 GB)

# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
path: xView # dataset root dir
train: images/autosplit_train.txt # train images (relative to 'path') 90% of 847 train images
val: images/autosplit_val.txt # val images (relative to 'path') 10% of 847 train images

# Classes
names:
  0: Fixed-wing Aircraft
  1: Small Aircraft
  2: Cargo Plane
  3: Helicopter
  4: Passenger Vehicle
  5: Small Car
  6: Bus
  7: Pickup Truck
  8: Utility Truck
  9: Truck
  10: Cargo Truck
  11: Truck w/Box
  12: Truck Tractor
  13: Trailer
  14: Truck w/Flatbed
  15: Truck w/Liquid
  16: Crane Truck
  17: Railway Vehicle
  18: Passenger Car
  19: Cargo Car
  20: Flat Car
  21: Tank car
  22: Locomotive
  23: Maritime Vessel
  24: Motorboat
  25: Sailboat
  26: Tugboat
  27: Barge
  28: Fishing Vessel
  29: Ferry
  30: Yacht
  31: Container Ship
  32: Oil Tanker
  33: Engineering Vehicle
  34: Tower crane
  35: Container Crane
  36: Reach Stacker
  37: Straddle Carrier
  38: Mobile Crane
  39: Dump Truck
  40: Haul Truck
  41: Scraper/Tractor
  42: Front loader/Bulldozer
  43: Excavator
  44: Cement Mixer
  45: Ground Grader
  46: Hut/Tent
  47: Shed
  48: Building
  49: Aircraft Hangar
  50: Damaged Building
  51: Facility
  52: Construction Site
  53: Vehicle Lot
  54: Helipad
  55: Storage Tank
  56: Shipping container lot
  57: Shipping Container
  58: Pylon
  59: Tower

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

  import numpy as np
  from PIL import Image

  from ultralytics.utils import TQDM
  from ultralytics.data.split import autosplit
  from ultralytics.utils.ops import xyxy2xywhn

  def convert_labels(fname=Path("xView/xView_train.geojson")):
      """Convert xView GeoJSON labels to YOLO format (classes 0-59) and save them as text files."""
      path = fname.parent
      with open(fname, encoding="utf-8") as f:
          print(f"Loading {fname}...")
          data = json.load(f)

      # Make dirs
      labels = path / "labels" / "train"
      shutil.rmtree(labels, ignore_errors=True)
      labels.mkdir(parents=True, exist_ok=True)

      # xView classes 11-94 to 0-59
      xview_class2index = [-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0, 1, 2, -1, 3, -1, 4, 5, 6, 7, 8, -1, 9, 10, 11,
                           12, 13, 14, 15, -1, -1, 16, 17, 18, 19, 20, 21, 22, -1, 23, 24, 25, -1, 26, 27, -1, 28, -1,
                           29, 30, 31, 32, 33, 34, 35, 36, 37, -1, 38, 39, 40, 41, 42, 43, 44, 45, -1, -1, -1, -1, 46,
                           47, 48, 49, -1, 50, 51, -1, 52, -1, -1, -1, 53, 54, -1, 55, -1, -1, 56, -1, 57, -1, 58, 59]

      shapes = {}
      for feature in TQDM(data["features"], desc=f"Converting {fname}"):
          p = feature["properties"]
          if p["bounds_imcoords"]:
              image_id = p["image_id"]
              image_file = path / "train_images" / image_id
              if image_file.exists():  # 1395.tif missing
                  try:
                      box = np.array([int(num) for num in p["bounds_imcoords"].split(",")])
                      assert box.shape[0] == 4, f"incorrect box shape {box.shape[0]}"
                      cls = p["type_id"]
                      cls = xview_class2index[int(cls)]  # xView class to 0-59
                      assert 59 >= cls >= 0, f"incorrect class index {cls}"

                      # Write YOLO label
                      if image_id not in shapes:
                          shapes[image_id] = Image.open(image_file).size
                      box = xyxy2xywhn(box[None].astype(float), w=shapes[image_id][0], h=shapes[image_id][1], clip=True)
                      with open((labels / image_id).with_suffix(".txt"), "a", encoding="utf-8") as f:
                          f.write(f"{cls} {' '.join(f'{x:.6f}' for x in box[0])}\n")  # write label.txt
                  except Exception as e:
                      print(f"WARNING: skipping one label for {image_file}: {e}")

  # Download manually from https://challenge.xviewdataset.org
  dir = Path(yaml["path"])  # dataset root dir
  # urls = [
  #     "https://d307kc0mrhucc3.cloudfront.net/train_labels.zip",  # train labels
  #     "https://d307kc0mrhucc3.cloudfront.net/train_images.zip",  # 15G, 847 train images
  #     "https://d307kc0mrhucc3.cloudfront.net/val_images.zip",  # 5G, 282 val images (no labels)
  # ]
  # download(urls, dir=dir)

  # Convert labels
  convert_labels(dir / "xView_train.geojson")

  # Move images
  images = Path(dir / "images")
  images.mkdir(parents=True, exist_ok=True)
  Path(dir / "train_images").rename(dir / "images" / "train")
  Path(dir / "val_images").rename(dir / "images" / "val")

  # Split
  autosplit(dir / "images" / "train")