mirrors/yolov5
1
0
Fork 0
mirror of https://github.com/ultralytics/yolov5.git synced 2025-06-03 14:49:29 +08:00
Code Issues Projects Releases Wiki Activity

Update dataset_stats() to list of dicts (#3657)

Browse Source 
* Update `dataset_stats()` to list of dicts

@KalenMike

* Update datasets.py
This commit is contained in:
Glenn Jocher 2021-06-17 13:59:52 +02:00 committed by GitHub
parent df7706d802
commit 9b6dba6207
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
utils/datasets.py
View File

@ -1099,6 +1099,11 @@ def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False):
autodownload: Attempt to download dataset if not found locally autodownload: Attempt to download dataset if not found locally
verbose: Print stats dictionary verbose: Print stats dictionary
""" """
def round_labels(labels):
# Update labels to integer class and 6 decimal place floats
return [[int(c), *[round(x, 6) for x in points]] for c, *points in labels]
with open(check_file(path)) as f: with open(check_file(path)) as f:
data = yaml.safe_load(f) # data dict data = yaml.safe_load(f) # data dict
check_dataset(data, autodownload) # download dataset if missing check_dataset(data, autodownload) # download dataset if missing
@ -1118,12 +1123,13 @@ def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False):
stats[split] = {'instance_stats': {'total': int(x.sum()), 'per_class': x.sum(0).tolist()}, stats[split] = {'instance_stats': {'total': int(x.sum()), 'per_class': x.sum(0).tolist()},
'image_stats': {'total': dataset.n, 'unlabelled': int(np.all(x == 0, 1).sum()), 'image_stats': {'total': dataset.n, 'unlabelled': int(np.all(x == 0, 1).sum()),
'per_class': (x > 0).sum(0).tolist()}, 'per_class': (x > 0).sum(0).tolist()},
'labels': {str(Path(k).name): v.tolist() for k, v in zip(dataset.img_files, dataset.labels)}} 'labels': [{str(Path(k).name): round_labels(v.tolist())} for k, v in
zip(dataset.img_files, dataset.labels)]}
# Save, print and return # Save, print and return
with open(cache_path.with_suffix('.json'), 'w') as f: with open(cache_path.with_suffix('.json'), 'w') as f:
json.dump(stats, f) # save stats *.json json.dump(stats, f) # save stats *.json
if verbose: if verbose:
print(yaml.dump([stats], sort_keys=False, default_flow_style=False)) print(json.dumps(stats, indent=2, sort_keys=False))
# print(json.dumps(stats, indent=2, sort_keys=False)) # print(yaml.dump([stats], sort_keys=False, default_flow_style=False))
return stats return stats