Add `data/utils.py` to tests (#4363)

tests/test_python.py

@@ -1,4 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
+
+import shutil
 from pathlib import Path
 
 import cv2
@@ -224,20 +226,22 @@ def test_results():
 
 def test_data_utils():
     # Test functions in ultralytics/data/utils.py
-    from ultralytics.data.utils import autosplit, zip_directory
+    from ultralytics.data.utils import HUBDatasetStats, autosplit, zip_directory
+    from ultralytics.utils.downloads import download
 
     # from ultralytics.utils.files import WorkingDirectory
     # with WorkingDirectory(ROOT.parent / 'tests'):
 
-    autosplit()
+    Path('tests/coco8.zip').unlink(missing_ok=True)
-    zip_directory(ROOT / 'assets')  # zip
+    Path('coco8.zip').unlink(missing_ok=True)
-    Path(ROOT / 'assets.zip').unlink()  # delete zip
+    download('https://github.com/ultralytics/hub/raw/master/example_datasets/coco8.zip', unzip=False)
-
+    shutil.move('coco8.zip', 'tests')
-    # from ultralytics.data.utils import HUBDatasetStats
+    shutil.rmtree('tests/coco8', ignore_errors=True)
-    # from ultralytics.utils.downloads import download
+    stats = HUBDatasetStats('tests/coco8.zip', task='detect')
-    # Path('coco8.zip').unlink(missing_ok=True)
+    stats.get_json(save=False)
-    # download('https://github.com/ultralytics/hub/raw/master/example_datasets/coco8.zip', unzip=False)
+    stats.process_images()
-    # shutil.move('coco8.zip', 'tests')
+
-    # stats = HUBDatasetStats('tests/coco8.zip', task='detect')
+    autosplit('tests/coco8')
-    # stats.get_json(save=False)
+    zip_directory('tests/coco8/images/val')  # zip
-    # stats.process_images()
+    shutil.rmtree('tests/coco8', ignore_errors=True)
+    shutil.rmtree('tests/coco8-hub', ignore_errors=True)

ultralytics/data/utils.py

@@ -364,8 +364,9 @@ class HUBDatasetStats:
 
     def __init__(self, path='coco128.yaml', task='detect', autodownload=False):
         """Initialize class."""
+        path = Path(path).resolve()
         LOGGER.info(f'Starting HUB dataset checks for {path}....')
-        zipped, data_dir, yaml_path = self._unzip(Path(path))
+        zipped, data_dir, yaml_path = self._unzip(path)
         try:
             # data = yaml_load(check_yaml(yaml_path))  # data dict
             data = check_det_dataset(yaml_path, autodownload)  # data dict
@@ -385,7 +386,7 @@ class HUBDatasetStats:
     def _find_yaml(dir):
         """Return data.yaml file."""
         files = list(dir.glob('*.yaml')) or list(dir.rglob('*.yaml'))  # try root level first and then recursive
-        assert files, f'No *.yaml file found in {dir.resolve()}'
+        assert files, f"No *.yaml file found in '{dir.resolve()}'"
         if len(files) > 1:
             files = [f for f in files if f.stem == dir.stem]  # prefer *.yaml files that match dir name
         assert len(files) == 1, f"Expected 1 *.yaml file in '{dir.resolve()}', but found {len(files)}.\n{files}"

ultralytics/utils/downloads.py

@@ -125,12 +125,12 @@ def unzip_file(file, path=None, exclude=('.DS_Store', '__MACOSX'), exist_ok=Fals
         if extract_path.exists() and any(extract_path.iterdir()) and not exist_ok:
             # If it exists and is not empty, return the path without unzipping
             LOGGER.info(f'Skipping {file} unzip (already unzipped)')
-            return path
+            return extract_path
 
         for f in tqdm(files, desc=f'Unzipping {file} to {Path(path).resolve()}...', unit='file', disable=not progress):
             zipObj.extract(f, path=path)
 
-    return path  # return unzip dir
+    return extract_path  # return unzip dir
 
 
 def check_disk_space(url='https://ultralytics.com/assets/coco128.zip', sf=1.5, hard=True):