Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Improved dataset error introspection #8091

Merged
merged 2 commits into from
Jun 3, 2022
Merged

Improved dataset error introspection #8091

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1284205
Improved dataset error introspection
glenn-jocher Jun 3, 2022
d5bd173
Update general.py
glenn-jocher Jun 3, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 8 additions & 5 deletions utils/general.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -448,8 +448,7 @@ def check_font(font=FONT, progress=False):


def check_dataset(data, autodownload=True):
# Download and/or unzip dataset if not found locally
# Usage: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128_with_yaml.zip
# Download, check and/or unzip dataset if not found locally

# Download (optional)
extract_dir = ''
Expand All @@ -463,6 +462,13 @@ def check_dataset(data, autodownload=True):
with open(data, errors='ignore') as f:
data = yaml.safe_load(f) # dictionary

# Checks
for k in 'train', 'val', 'nc':
assert k in data, emojis(f"data.yaml '{k}:' field missing ❌")
if 'names' not in data:
LOGGER.warning(emojis("data.yaml 'names:' field missing ⚠, assigning default names 'class0', 'class1', etc."))
data['names'] = [f'class{i}' for i in range(data['nc'])] # default names

# Resolve paths
path = Path(extract_dir or data.get('path') or '') # optional 'path' default to '.'
if not path.is_absolute():
Expand All @@ -472,9 +478,6 @@ def check_dataset(data, autodownload=True):
data[k] = str(path / data[k]) if isinstance(data[k], str) else [str(path / x) for x in data[k]]

# Parse yaml
assert 'nc' in data, "Dataset 'nc' key missing."
if 'names' not in data:
data['names'] = [f'class{i}' for i in range(data['nc'])] # assign class names if missing
train, val, test, s = (data.get(x) for x in ('train', 'val', 'test', 'download'))
if val:
val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path
Expand Down