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>

data/Objects365.yaml

@@ -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)