You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
152 lines
5.1 KiB
152 lines
5.1 KiB
# Ultralytics YOLO 🚀, AGPL-3.0 license |
|
# DIUx xView 2018 Challenge https://challenge.xviewdataset.org by U.S. National Geospatial-Intelligence Agency (NGA) |
|
# -------- DOWNLOAD DATA MANUALLY and jar xf val_images.zip to 'datasets/xView' before running 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: ../datasets/xView # dataset root dir |
|
train: images/autosplit_train.txt # train images (relative to 'path') 90% of 847 train images |
|
val: images/autosplit_val.txt # train 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 |
|
import os |
|
from pathlib import Path |
|
|
|
import numpy as np |
|
from PIL import Image |
|
from tqdm import tqdm |
|
|
|
from ultralytics.data.utils import autosplit |
|
from ultralytics.utils.ops import xyxy2xywhn |
|
|
|
|
|
def convert_labels(fname=Path('xView/xView_train.geojson')): |
|
# Convert xView geoJSON labels to YOLO format |
|
path = fname.parent |
|
with open(fname) as f: |
|
print(f'Loading {fname}...') |
|
data = json.load(f) |
|
|
|
# Make dirs |
|
labels = Path(path / 'labels' / 'train') |
|
os.system(f'rm -rf {labels}') |
|
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']: |
|
id = p['image_id'] |
|
file = path / 'train_images' / id |
|
if 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 0-60 |
|
assert 59 >= cls >= 0, f'incorrect class index {cls}' |
|
|
|
# Write YOLO label |
|
if id not in shapes: |
|
shapes[id] = Image.open(file).size |
|
box = xyxy2xywhn(box[None].astype(np.float), w=shapes[id][0], h=shapes[id][1], clip=True) |
|
with open((labels / id).with_suffix('.txt'), 'a') 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 {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')
|
|
|