NGA xView 2018 Dataset Auto-Download (#3775)

* update clip_coords for numpy

* uncomment

* cleanup

* Add autosplits

* fix

* cleanup

utils/datasets.py

@@ -985,7 +985,7 @@ def create_folder(path='./new'):
     os.makedirs(path)  # make new output folder
 
 
-def flatten_recursive(path='../coco128'):
+def flatten_recursive(path='../datasets/coco128'):
     # Flatten a recursive directory by bringing all files to top level
     new_path = Path(path + '_flat')
     create_folder(new_path)
@@ -993,7 +993,7 @@ def flatten_recursive(path='../coco128'):
         shutil.copyfile(file, new_path / Path(file).name)
 
 
-def extract_boxes(path='../coco128/'):  # from utils.datasets import *; extract_boxes('../coco128')
+def extract_boxes(path='../datasets/coco128'):  # from utils.datasets import *; extract_boxes()
     # Convert detection dataset into classification dataset, with one directory per class
 
     path = Path(path)  # images dir
@@ -1028,27 +1028,28 @@ def extract_boxes(path='../coco128/'):  # from utils.datasets import *; extract_
                     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), annotated_only=False):
+def autosplit(path='../datasets/coco128/images', weights=(0.9, 0.1, 0.0), annotated_only=False):
     """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
-    Usage: from utils.datasets import *; autosplit('../coco128')
+    Usage: from utils.datasets import *; autosplit()
     Arguments
-        path:           Path to images directory
-        weights:        Train, val, test weights (list)
-        annotated_only: Only use images with an annotated txt file
+        path:            Path to images directory
+        weights:         Train, val, test weights (list, tuple)
+        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
     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
 
     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
+    [(path.parent / x).unlink(missing_ok=True) for x in txt]  # 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 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
+            with open(path.parent / txt[i], 'a') as f:
+                f.write('./' + img.relative_to(path.parent).as_posix() + '\n')  # add image to txt file
 
 
 def verify_image_label(args):