Add optional dataset.yaml path attribute (#3753)

* Add optional dataset.yaml `path` attribute

@KalenMike

* pass locals to python scripts

* handle lists

* update coco128.yaml

* Capitalize first letter

* add test key

* finalize GlobalWheat2020.yaml

* finalize objects365.yaml

* finalize SKU-110K.yaml

* finalize SKU-110K.yaml

* finalize VisDrone.yaml

* NoneType fix

* update download comment

* voc to VOC

* update

* update VOC.yaml

* update VOC.yaml

* remove dashes

* delete get_voc.sh

* force coco and coco128 to ../datasets

* Capitalize Argoverse_HD.yaml

* Capitalize Objects365.yaml

* update Argoverse_HD.yaml

* coco segments fix

* VOC single-thread

* update Argoverse_HD.yaml

* update data_dict in test handling

* create root

data/coco.yaml

@@ -1,23 +1,19 @@
 # COCO 2017 dataset http://cocodataset.org
 # Train command: python train.py --data coco.yaml
 # Default dataset location is next to YOLOv5:
-#   /parent_folder
-#     /coco
+#   /parent
+#     /datasets/coco
 #     /yolov5
 
 
-# download command/URL (optional)
-download: bash data/scripts/get_coco.sh
+# Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..]
+path: ../datasets/coco  # dataset root dir
+train: train2017.txt  # train images (relative to 'path') 118287 images
+val: val2017.txt  # train images (relative to 'path') 5000 images
+test: test-dev2017.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
 
-# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
-train: ../coco/train2017.txt  # 118287 images
-val: ../coco/val2017.txt  # 5000 images
-test: ../coco/test-dev2017.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
-
-# number of classes
-nc: 80
-
-# class names
+# Classes
+nc: 80  # number of classes
 names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
          'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
          'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
@@ -26,10 +22,22 @@ names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', '
          'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
          'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
          'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
-         'hair drier', 'toothbrush' ]
+         'hair drier', 'toothbrush' ]  # class names
 
-# Print classes
-# with open('data/coco.yaml') as f:
-#   d = yaml.safe_load(f)  # dict
-#   for i, x in enumerate(d['names']):
-#     print(i, x)
+
+# Download script/URL (optional)
+download: |
+  from utils.general import download, Path
+
+  # Download labels
+  segments = False  # segment or box labels
+  dir = Path(yaml['path'])  # dataset root dir
+  url = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/'
+  urls = [url + ('coco2017labels-segments.zip' if segments else 'coco2017labels.zip')]  # labels
+  download(urls, dir=dir.parent)
+
+  # Download data
+  urls = ['http://images.cocodataset.org/zips/train2017.zip',  # 19G, 118k images
+          'http://images.cocodataset.org/zips/val2017.zip',  # 1G, 5k images
+          'http://images.cocodataset.org/zips/test2017.zip']  # 7G, 41k images (optional)
+  download(urls, dir=dir / 'images', threads=3)