Be able to create dataset from annotated images only

utils/datasets.py

@@ -1032,20 +1032,24 @@ def extract_boxes(path='../coco128/'):  # from utils.datasets import *; extract_
                     b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
                     assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'
 
-
-def autosplit(path='../coco128', weights=(0.9, 0.1, 0.0)):  # from utils.datasets import *; autosplit('../coco128')
+def autosplit(path='../coco128', weights=(0.9, 0.1, 0.0), annotated_only=False):
     """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
-    # Arguments
-        path:       Path to images directory
-        weights:    Train, val, test weights (list)
+    Usage: from utils.datasets import *; autosplit('../coco128')
+    Arguments
+        path:           Path to images directory
+        weights:        Train, val, test weights (list)
+        annotated_only: Only use images with an annotated txt file
     """
     path = Path(path)  # images dir
-    files = list(path.rglob('*.*'))
+    files = sum([list(path.rglob(f"*.{img_ext}")) for img_ext in img_formats], [])  # image files only
     n = len(files)  # number of files
     indices = random.choices([0, 1, 2], weights=weights, k=n)  # assign each image to a split
+
     txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt']  # 3 txt files
     [(path / x).unlink() for x in txt if (path / x).exists()]  # remove existing
+
+    print(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only)
     for i, img in tqdm(zip(indices, files), total=n):
-        if img.suffix[1:] in img_formats:
+        if not annotated_only or Path(img2label_paths([str(img)])[0]).exists():  # check label
             with open(path / txt[i], 'a') as f:
                 f.write(str(img) + '\n')  # add image to txt file