Revert "Remove dataset_stats() autodownload capability (#6303)" (#6442)

This reverts commit 3119b2f27c.
This commit is contained in:
Glenn Jocher authored and GitHub committed 2022-01-26 19:10:59 +01:00
1 parent 3b7ac28ed1
commit fe7de6a82d
1 file changed
+4 -3
+4 -3
View File
@@ -936,10 +936,11 @@ def verify_image_label(args):
return [None, None, None, None, nm, nf, ne, nc, msg] return [None, None, None, None, nm, nf, ne, nc, msg]
def dataset_stats(path='coco128.yaml', verbose=False, profile=False, hub=False): def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profile=False, hub=False):
""" Return dataset statistics dictionary with images and instances counts per split per class """ Return dataset statistics dictionary with images and instances counts per split per class
To run in parent directory: export PYTHONPATH="$PWD/yolov5" To run in parent directory: export PYTHONPATH="$PWD/yolov5"
Usage: from utils.datasets import *; dataset_stats('../datasets/coco128_with_yaml.zip') Usage1: from utils.datasets import *; dataset_stats('coco128.yaml', autodownload=True)
Usage2: from utils.datasets import *; dataset_stats('../datasets/coco128_with_yaml.zip')
Arguments Arguments
path: Path to data.yaml or data.zip (with data.yaml inside data.zip) path: Path to data.yaml or data.zip (with data.yaml inside data.zip)
autodownload: Attempt to download dataset if not found locally autodownload: Attempt to download dataset if not found locally
@@ -983,7 +984,7 @@ def dataset_stats(path='coco128.yaml', verbose=False, profile=False, hub=False):
data = yaml.safe_load(f) # data dict data = yaml.safe_load(f) # data dict
if zipped: if zipped:
data['path'] = data_dir # TODO: should this be dir.resolve()? data['path'] = data_dir # TODO: should this be dir.resolve()?
check_dataset(data, autodownload=False) check_dataset(data, autodownload) # download dataset if missing
hub_dir = Path(data['path'] + ('-hub' if hub else '')) hub_dir = Path(data['path'] + ('-hub' if hub else ''))
stats = {'nc': data['nc'], 'names': data['names']} # statistics dictionary stats = {'nc': data['nc'], 'names': data['names']} # statistics dictionary
for split in 'train', 'val', 'test': for split in 'train', 'val', 'test':