`ultralytics 8.0.157` fix `unzip_file()` bug (#4407)

Co-authored-by: Nadim Bou Alwan <64587372+nadinator@users.noreply.github.com>

docs/guides/kfold-cross-validation.md

@@ -198,7 +198,7 @@ The ideal scenario is for all class ratios to be reasonably similar for each spl
     
         with open(dataset_yaml, 'w') as ds_y:
             yaml.safe_dump({
-                'path': save_path.as_posix(),
+                'path': split_dir.as_posix(),
                 'train': 'train',
                 'val': 'val',
                 'names': classes

docs/reference/data/utils.md

@@ -53,14 +53,6 @@ keywords: Ultralytics, data utils, YOLO, img2label_paths, exif_size, polygon2mas
 ## ::: ultralytics.data.utils.compress_one_image
 <br><br>
 
----
-## ::: ultralytics.data.utils.delete_dsstore
-<br><br>
-
----
-## ::: ultralytics.data.utils.zip_directory
-<br><br>
-
 ---
 ## ::: ultralytics.data.utils.autosplit
 <br><br>

docs/reference/utils/downloads.md

@@ -13,6 +13,10 @@ keywords: Ultralytics, YOLO, download utilities, is_url, check_disk_space, get_g
 ## ::: ultralytics.utils.downloads.is_url
 <br><br>
 
+---
+## ::: ultralytics.utils.downloads.delete_dsstore
+<br><br>
+
 ---
 ## ::: ultralytics.utils.downloads.zip_directory
 <br><br>

tests/test_cli.py

@@ -7,7 +7,7 @@ import pytest
 
 from ultralytics.utils import ROOT, SETTINGS
 
-WEIGHT_DIR = Path(SETTINGS['weights_dir'])
+WEIGHTS_DIR = Path(SETTINGS['weights_dir'])
 TASK_ARGS = [
     ('detect', 'yolov8n', 'coco8.yaml'),
     ('segment', 'yolov8n-seg', 'coco8-seg.yaml'),
@@ -40,17 +40,17 @@ def test_train(task, model, data):
 
 @pytest.mark.parametrize('task,model,data', TASK_ARGS)
 def test_val(task, model, data):
-    run(f'yolo val {task} model={WEIGHT_DIR / model}.pt data={data} imgsz=32')
+    run(f'yolo val {task} model={WEIGHTS_DIR / model}.pt data={data} imgsz=32')
 
 
 @pytest.mark.parametrize('task,model,data', TASK_ARGS)
 def test_predict(task, model, data):
-    run(f"yolo predict model={WEIGHT_DIR / model}.pt source={ROOT / 'assets'} imgsz=32 save save_crop save_txt")
+    run(f"yolo predict model={WEIGHTS_DIR / model}.pt source={ROOT / 'assets'} imgsz=32 save save_crop save_txt")
 
 
 @pytest.mark.parametrize('model,format', EXPORT_ARGS)
 def test_export(model, format):
-    run(f'yolo export model={WEIGHT_DIR / model}.pt format={format} imgsz=32')
+    run(f'yolo export model={WEIGHTS_DIR / model}.pt format={format} imgsz=32')
 
 
 def test_rtdetr(task='detect', model='yolov8n-rtdetr.yaml', data='coco8.yaml'):
@@ -59,7 +59,7 @@ def test_rtdetr(task='detect', model='yolov8n-rtdetr.yaml', data='coco8.yaml'):
     run(f"yolo predict {task} model={model} source={ROOT / 'assets/bus.jpg'} imgsz=640 save save_crop save_txt")
 
 
-def test_fastsam(task='segment', model=WEIGHT_DIR / 'FastSAM-s.pt', data='coco8-seg.yaml'):
+def test_fastsam(task='segment', model=WEIGHTS_DIR / 'FastSAM-s.pt', data='coco8-seg.yaml'):
     source = ROOT / 'assets/bus.jpg'
 
     run(f'yolo segment val {task} model={model} data={data} imgsz=32')
@@ -95,7 +95,7 @@ def test_mobilesam():
     from ultralytics import SAM
 
     # Load the model
-    model = SAM(WEIGHT_DIR / 'mobile_sam.pt')
+    model = SAM(WEIGHTS_DIR / 'mobile_sam.pt')
 
     # Source
     source = ROOT / 'assets/zidane.jpg'

tests/test_python.py

@@ -26,7 +26,7 @@ TMP = (ROOT / '../tests/tmp').resolve()  # temp directory for test files
 
 def test_model_forward():
     model = YOLO(CFG)
-    model(SOURCE, imgsz=32)
+    model(SOURCE, imgsz=32, augment=True)
 
 
 def test_model_info():
@@ -120,8 +120,8 @@ def test_train_scratch():
 
 
 def test_train_pretrained():
-    model = YOLO(MODEL)
-    model.train(data='coco8.yaml', epochs=1, imgsz=32, cache='ram')  # test RAM caching
+    model = YOLO(WEIGHTS_DIR / 'yolov8n-seg.pt')
+    model.train(data='coco8-seg.yaml', epochs=1, imgsz=32, cache='ram', copy_paste=0.5, mixup=0.5)  # test RAM caching
     model(SOURCE)
 
 
@@ -232,7 +232,8 @@ def test_results():
 @pytest.mark.skipif(not ONLINE, reason='environment is offline')
 def test_data_utils():
     # Test functions in ultralytics/data/utils.py
-    from ultralytics.data.utils import HUBDatasetStats, autosplit, zip_directory
+    from ultralytics.data.utils import HUBDatasetStats, autosplit
+    from ultralytics.utils.downloads import zip_directory
 
     # from ultralytics.utils.files import WorkingDirectory
     # with WorkingDirectory(ROOT.parent / 'tests'):
@@ -240,7 +241,7 @@ def test_data_utils():
     download('https://github.com/ultralytics/hub/raw/master/example_datasets/coco8.zip', unzip=False)
     shutil.move('coco8.zip', TMP)
     stats = HUBDatasetStats(TMP / 'coco8.zip', task='detect')
-    stats.get_json(save=False)
+    stats.get_json(save=True)
     stats.process_images()
 
     autosplit(TMP / 'coco8')
@@ -267,3 +268,11 @@ def test_events():
     cfg = copy(DEFAULT_CFG)  # does not require deepcopy
     cfg.mode = 'test'
     events(cfg)
+
+
+def test_utils_checks():
+    from ultralytics.utils.checks import check_yolov5u_filename, git_describe
+
+    check_yolov5u_filename('yolov5.pt')
+    # check_imshow(warn=True)
+    git_describe(ROOT)

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = '8.0.156'
+__version__ = '8.0.157'
 
 from ultralytics.hub import start
 from ultralytics.models import RTDETR, SAM, YOLO

ultralytics/data/utils.py

@@ -499,58 +499,6 @@ def compress_one_image(f, f_new=None, max_dim=1920, quality=50):
         cv2.imwrite(str(f_new or f), im)
 
 
-def delete_dsstore(path):
-    """
-    Deletes all ".DS_store" files under a specified directory.
-
-    Args:
-        path (str, optional): The directory path where the ".DS_store" files should be deleted.
-
-    Example:
-        ```python
-        from ultralytics.data.utils import delete_dsstore
-
-        delete_dsstore('path/to/dir')
-        ```
-
-    Note:
-        ".DS_store" files are created by the Apple operating system and contain metadata about folders and files. They
-        are hidden system files and can cause issues when transferring files between different operating systems.
-    """
-    # Delete Apple .DS_store files
-    files = list(Path(path).rglob('.DS_store'))
-    LOGGER.info(f'Deleting *.DS_store files: {files}')
-    for f in files:
-        f.unlink()
-
-
-def zip_directory(dir, use_zipfile_library=True):
-    """
-    Zips a directory and saves the archive to the specified output path. Equivalent to 'zip -r coco8.zip coco8/'
-
-    Args:
-        dir (str): The path to the directory to be zipped.
-        use_zipfile_library (bool): Whether to use zipfile library or shutil for zipping.
-
-    Example:
-        ```python
-        from ultralytics.data.utils import zip_directory
-
-        zip_directory('/path/to/dir')
-        ```
-    """
-    delete_dsstore(dir)
-    if use_zipfile_library:
-        dir = Path(dir)
-        with zipfile.ZipFile(dir.with_suffix('.zip'), 'w', zipfile.ZIP_DEFLATED) as zip_file:
-            for file_path in dir.glob('**/*'):
-                if file_path.is_file():
-                    zip_file.write(file_path, file_path.relative_to(dir))
-    else:
-        import shutil
-        shutil.make_archive(dir, 'zip', dir)
-
-
 def autosplit(path=DATASETS_DIR / 'coco8/images', weights=(0.9, 0.1, 0.0), annotated_only=False):
     """
     Automatically split a dataset into train/val/test splits and save the resulting splits into autosplit_*.txt files.

ultralytics/utils/checks.py

@@ -164,7 +164,6 @@ def check_latest_pypi_version(package_name='ultralytics'):
         response = requests.get(f'https://pypi.org/pypi/{package_name}/json', timeout=3)
         if response.status_code == 200:
             return response.json()['info']['version']
-    return None
 
 
 def check_pip_update_available():

ultralytics/utils/downloads.py

@@ -39,6 +39,31 @@ def is_url(url, check=True):
     return False
 
 
+def delete_dsstore(path):
+    """
+    Deletes all ".DS_store" files under a specified directory.
+
+    Args:
+        path (str, optional): The directory path where the ".DS_store" files should be deleted.
+
+    Example:
+        ```python
+        from ultralytics.data.utils import delete_dsstore
+
+        delete_dsstore('path/to/dir')
+        ```
+
+    Note:
+        ".DS_store" files are created by the Apple operating system and contain metadata about folders and files. They
+        are hidden system files and can cause issues when transferring files between different operating systems.
+    """
+    # Delete Apple .DS_store files
+    files = list(Path(path).rglob('.DS_store'))
+    LOGGER.info(f'Deleting *.DS_store files: {files}')
+    for f in files:
+        f.unlink()
+
+
 def zip_directory(directory, compress=True, exclude=('.DS_Store', '__MACOSX'), progress=True):
     """
     Zips the contents of a directory, excluding files containing strings in the exclude list.
@@ -62,6 +87,7 @@ def zip_directory(directory, compress=True, exclude=('.DS_Store', '__MACOSX'), p
     """
     from zipfile import ZIP_DEFLATED, ZIP_STORED, ZipFile
 
+    delete_dsstore(directory)
     directory = Path(directory)
     if not directory.is_dir():
         raise FileNotFoundError(f"Directory '{directory}' does not exist.")
@@ -117,20 +143,22 @@ def unzip_file(file, path=None, exclude=('.DS_Store', '__MACOSX'), exist_ok=Fals
         files = [f for f in zipObj.namelist() if all(x not in f for x in exclude)]
         top_level_dirs = {Path(f).parts[0] for f in files}
 
-        if len(top_level_dirs) > 1 or not files[0].endswith('/'):
-            path = Path(path) / Path(file).stem  # define new unzip directory
+        if len(top_level_dirs) > 1 or not files[0].endswith('/'):  # zip has multiple files at top level
+            path = extract_path = Path(path) / Path(file).stem  # i.e. ../datasets/coco8
+        else:  # zip has 1 top-level directory
+            extract_path = path  # i.e. ../datasets
+            path = Path(path) / list(top_level_dirs)[0]  # i.e. ../datasets/coco8
 
         # Check if destination directory already exists and contains files
-        extract_path = Path(path) / list(top_level_dirs)[0]
-        if extract_path.exists() and any(extract_path.iterdir()) and not exist_ok:
+        if path.exists() and any(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 extract_path
+            return path
 
         for f in tqdm(files, desc=f'Unzipping {file} to {Path(path).resolve()}...', unit='file', disable=not progress):
-            zipObj.extract(f, path=path)
+            zipObj.extract(f, path=extract_path)
 
-    return extract_path  # return unzip dir
+    return path  # return unzip dir
 
 
 def check_disk_space(url='https://ultralytics.com/assets/coco128.zip', sf=1.5, hard=True):