瀏覽代碼

Update Objects365.yaml to include the official validation set (#5194)

* Update Objects365.yaml

Download the official Objects365 validation set and convert the labels

* Enforce 4-space indent, reformat and cleanup

* shorten list comprehension

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
modifyDataloader
Farley Lai GitHub 3 年之前
父節點
當前提交
fc3606420d
沒有發現已知的金鑰在資料庫的簽署中 GPG 金鑰 ID: 4AEE18F83AFDEB23
共有 1 個檔案被更改,包括 40 行新增33 行删除
  1. +40
    -33
      data/Objects365.yaml

+ 40
- 33
data/Objects365.yaml 查看文件

@@ -62,43 +62,50 @@ names: ['Person', 'Sneakers', 'Chair', 'Other Shoes', 'Hat', 'Car', 'Lamp', 'Gla
download: |
from pycocotools.coco import COCO
from tqdm import tqdm
from utils.general import download, Path
# Make Directories
dir = Path(yaml['path']) # dataset root dir
for p in 'images', 'labels':
(dir / p).mkdir(parents=True, exist_ok=True)
for q in 'train', 'val':
(dir / p / q).mkdir(parents=True, exist_ok=True)

# Download
url = "https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/train/"
download([url + 'zhiyuan_objv2_train.tar.gz'], dir=dir, delete=False) # annotations json
download([url + f for f in [f'patch{i}.tar.gz' for i in range(51)]], dir=dir / 'images' / 'train',
curl=True, delete=False, threads=8)

# Move
train = dir / 'images' / 'train'
for f in tqdm(train.rglob('*.jpg'), desc=f'Moving images'):
f.rename(train / f.name) # move to /images/train

# Labels
coco = COCO(dir / 'zhiyuan_objv2_train.json')
names = [x["name"] for x in coco.loadCats(coco.getCatIds())]
for cid, cat in enumerate(names):
catIds = coco.getCatIds(catNms=[cat])
imgIds = coco.getImgIds(catIds=catIds)
for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'):
width, height = im["width"], im["height"]
path = Path(im["file_name"]) # image filename
try:
with open(dir / 'labels' / 'train' / path.with_suffix('.txt').name, 'a') as file:
annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None)
for a in coco.loadAnns(annIds):
x, y, w, h = a['bbox'] # bounding box in xywh (xy top-left corner)
x, y = x + w / 2, y + h / 2 # xy to center
file.write(f"{cid} {x / width:.5f} {y / height:.5f} {w / width:.5f} {h / height:.5f}\n")

except Exception as e:
print(e)
# Train, Val Splits
for split, patches in [('train', 50 + 1), ('val', 43 + 1)]:
print(f"Processing {split} in {patches} patches ...")
images, labels = dir / 'images' / split, dir / 'labels' / split
# Download
url = f"https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/{split}/"
if split == 'train':
download([f'{url}zhiyuan_objv2_{split}.tar.gz'], dir=dir, delete=False) # annotations json
download([f'{url}patch{i}.tar.gz' for i in range(patches)], dir=images, curl=True, delete=False, threads=8)
elif split == 'val':
download([f'{url}zhiyuan_objv2_{split}.json'], dir=dir, delete=False) # annotations json
download([f'{url}images/v1/patch{i}.tar.gz' for i in range(15 + 1)], dir=images, curl=True, delete=False, threads=8)
download([f'{url}images/v2/patch{i}.tar.gz' for i in range(16, patches)], dir=images, curl=True, delete=False, threads=8)
# Move
for f in tqdm(images.rglob('*.jpg'), desc=f'Moving {split} images'):
f.rename(images / f.name) # move to /images/{split}
# Labels
coco = COCO(dir / f'zhiyuan_objv2_{split}.json')
names = [x["name"] for x in coco.loadCats(coco.getCatIds())]
for cid, cat in enumerate(names):
catIds = coco.getCatIds(catNms=[cat])
imgIds = coco.getImgIds(catIds=catIds)
for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'):
width, height = im["width"], im["height"]
path = Path(im["file_name"]) # image filename
try:
with open(labels / path.with_suffix('.txt').name, 'a') as file:
annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None)
for a in coco.loadAnns(annIds):
x, y, w, h = a['bbox'] # bounding box in xywh (xy top-left corner)
x, y = x + w / 2, y + h / 2 # xy to center
file.write(f"{cid} {x / width:.5f} {y / height:.5f} {w / width:.5f} {h / height:.5f}\n")
except Exception as e:
print(e)

Loading…
取消
儲存