Objects365 Update

data/objects365.yaml

@@ -55,3 +55,43 @@ names: [ 'Person', 'Sneakers', 'Chair', 'Other Shoes', 'Hat', 'Car', 'Lamp', 'Gl
          'Scallop', 'Noddles', 'Comb', 'Dumpling', 'Oyster', 'Table Tennis paddle', 'Cosmetics Brush/Eyeliner Pencil',
          'Chainsaw', 'Eraser', 'Lobster', 'Durian', 'Okra', 'Lipstick', 'Cosmetics Mirror', 'Curling', 'Table Tennis' ]
 
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+download: |
+  from pycocotools.coco import COCO
+  from tqdm import tqdm
+
+  from utils.general import download, Path
+
+  # Make Directories
+  dir = Path('../datasets/objects365')  # dataset directory
+  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)  # 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)
+
+  # 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}/{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)

utils/general.py

@@ -193,7 +193,7 @@ def check_dataset(dict):
                 raise Exception('Dataset not found.')
 
 
-def download(url, dir='.', unzip=True, curl=False, threads=1):
+def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1):
     # Multi-threaded file download and unzip function
     def download_one(url, dir):
         # Download 1 file
@@ -207,9 +207,12 @@ def download_one(url, dir):
         if unzip and f.suffix in ('.zip', '.gz'):
             print(f'Unzipping {f}...')
             if f.suffix == '.zip':
-                os.system(f'unzip -qo {f} -d {dir} && rm {f}')  # unzip -quiet -overwrite
+                s = f'unzip -qo {f} -d {dir} && rm {f}'  # unzip -quiet -overwrite
             elif f.suffix == '.gz':
-                os.system(f'tar xfz {f} --directory {f.parent} && rm {f}')  # unzip
+                s = f'tar xfz {f} --directory {f.parent}'  # unzip
+            if delete:  # delete zip file after unzip
+                s += f' && rm {f}'
+            os.system(s)
 
     dir = Path(dir)
     dir.mkdir(parents=True, exist_ok=True)  # make directory