autosplit: take image files with uppercase extensions into account (#…

…5269)

* take image files with uppercase extensions into account in autosplit

* case fix

* Refactor implementation

Removes additional variable (capital variable names are also only for global variables), and uses the same methodology as implemented earlier in datasets.py L409.

* Remove redundant rglob characters

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

utils/datasets.py

@@ -396,7 +396,7 @@ def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, r
                 p = Path(p)  # os-agnostic
                 if p.is_dir():  # dir
                     f += glob.glob(str(p / '**' / '*.*'), recursive=True)
-                    # f = list(p.rglob('**/*.*'))  # pathlib
+                    # f = list(p.rglob('*.*'))  # pathlib
                 elif p.is_file():  # file
                     with open(p, 'r') as t:
                         t = t.read().strip().splitlines()
@@ -406,7 +406,7 @@ def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, r
                 else:
                     raise Exception(f'{prefix}{p} does not exist')
             self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS])
-            # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in img_formats])  # pathlib
+            # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS])  # pathlib
             assert self.img_files, f'{prefix}No images found'
         except Exception as e:
             raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {HELP_URL}')
@@ -866,7 +866,7 @@ def autosplit(path='../datasets/coco128/images', weights=(0.9, 0.1, 0.0), annota
         annotated_only:  Only use images with an annotated txt file
     """
     path = Path(path)  # images dir
-    files = sum([list(path.rglob(f"*.{img_ext}")) for img_ext in IMG_FORMATS], [])  # image files only
+    files = sorted([x for x in path.rglob('*.*') if x.suffix[1:].lower() in IMG_FORMATS])  # image files only
     n = len(files)  # number of files
     random.seed(0)  # for reproducibility
     indices = random.choices([0, 1, 2], weights=weights, k=n)  # assign each image to a split