xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ultralytics 8.0.151 add DOTAv2.yaml for OBB training (#4258)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Kayzwer <68285002+Kayzwer@users.noreply.github.com>
This commit is contained in:
Glenn Jocher
2023-08-10 00:55:36 +02:00
committed by GitHub
parent a76af55533
commit c9be1f3cce
46 changed files with 805 additions and 303 deletions
Download Patch File Download Diff File Expand all files Collapse all files

112
ultralytics/data/converter.py
View File

@ -117,6 +117,97 @@ def convert_coco(labels_dir='../coco/annotations/', use_segments=False, use_keyp
file.write(('%g ' * len(line)).rstrip() % line + '\n')
def convert_dota_to_yolo_obb(dota_root_path: str):
"""
Converts DOTA dataset annotations to YOLO OBB (Oriented Bounding Box) format.
The function processes images in the 'train' and 'val' folders of the DOTA dataset. For each image, it reads the
associated label from the original labels directory and writes new labels in YOLO OBB format to a new directory.
Args:
dota_root_path (str): The root directory path of the DOTA dataset.
Example:
```python
from ultralytics.data.converter import convert_dota_to_yolo_obb
convert_dota_to_yolo_obb('path/to/DOTA')
```
Notes:
The directory structure assumed for the DOTA dataset:
- DOTA
- images
- train
- val
- labels
- train_original
- val_original
After the function execution, the new labels will be saved in:
- DOTA
- labels
- train
- val
"""
dota_root_path = Path(dota_root_path)
# Class names to indices mapping
class_mapping = {
'plane': 0,
'ship': 1,
'storage-tank': 2,
'baseball-diamond': 3,
'tennis-court': 4,
'basketball-court': 5,
'ground-track-field': 6,
'harbor': 7,
'bridge': 8,
'large-vehicle': 9,
'small-vehicle': 10,
'helicopter': 11,
'roundabout': 12,
'soccer ball-field': 13,
'swimming-pool': 14,
'container-crane': 15,
'airport': 16,
'helipad': 17}
def convert_label(image_name, image_width, image_height, orig_label_dir, save_dir):
orig_label_path = orig_label_dir / f'{image_name}.txt'
save_path = save_dir / f'{image_name}.txt'
with orig_label_path.open('r') as f, save_path.open('w') as g:
lines = f.readlines()
for line in lines:
parts = line.strip().split()
if len(parts) < 9:
continue
class_name = parts[8]
class_idx = class_mapping[class_name]
coords = [float(p) for p in parts[:8]]
normalized_coords = [
coords[i] / image_width if i % 2 == 0 else coords[i] / image_height for i in range(8)]
formatted_coords = ['{:.6g}'.format(coord) for coord in normalized_coords]
g.write(f"{class_idx} {' '.join(formatted_coords)}\n")
for phase in ['train', 'val']:
image_dir = dota_root_path / 'images' / phase
orig_label_dir = dota_root_path / 'labels' / f'{phase}_original'
save_dir = dota_root_path / 'labels' / phase
save_dir.mkdir(parents=True, exist_ok=True)
image_paths = list(image_dir.iterdir())
for image_path in tqdm(image_paths, desc=f'Processing {phase} images'):
if image_path.suffix != '.png':
continue
image_name_without_ext = image_path.stem
img = cv2.imread(str(image_path))
h, w = img.shape[:2]
convert_label(image_name_without_ext, w, h, orig_label_dir, save_dir)
def rle2polygon(segmentation):
"""
Convert Run-Length Encoding (RLE) mask to polygon coordinates.
@ -209,24 +300,3 @@ def merge_multi_segment(segments):
nidx = abs(idx[1] - idx[0])
s.append(segments[i][nidx:])
return s
def delete_dsstore(path='../datasets'):
"""Delete Apple .DS_Store files in the specified directory and its subdirectories."""
from pathlib import Path
files = list(Path(path).rglob('.DS_store'))
print(files)
for f in files:
f.unlink()
if __name__ == '__main__':
source = 'COCO'
if source == 'COCO':
convert_coco(
'../datasets/coco/annotations', # directory with *.json
use_segments=False,
use_keypoints=True,
cls91to80=False)

46
ultralytics/data/utils.py
View File

@ -24,7 +24,7 @@ from ultralytics.utils.checks import check_file, check_font, is_ascii
from ultralytics.utils.downloads import download, safe_download, unzip_file
from ultralytics.utils.ops import segments2boxes
HELP_URL = 'See https://docs.ultralytics.com/datasets/detect for YOLO dataset format help.'
HELP_URL = 'See https://docs.ultralytics.com/datasets/detect for dataset formatting guidance.'
IMG_FORMATS = 'bmp', 'dng', 'jpeg', 'jpg', 'mpo', 'png', 'tif', 'tiff', 'webp', 'pfm' # image suffixes
VID_FORMATS = 'asf', 'avi', 'gif', 'm4v', 'mkv', 'mov', 'mp4', 'mpeg', 'mpg', 'ts', 'wmv', 'webm' # video suffixes
PIN_MEMORY = str(os.getenv('PIN_MEMORY', True)).lower() == 'true' # global pin_memory for dataloaders
@ -289,9 +289,6 @@ def check_cls_dataset(dataset: str, split=''):
- 'test' (Path): The directory path containing the test set of the dataset.
- 'nc' (int): The number of classes in the dataset.
- 'names' (dict): A dictionary of class names in the dataset.
Raises:
FileNotFoundError: If the specified dataset is not found and cannot be downloaded.
"""
dataset = Path(dataset)
@ -329,13 +326,16 @@ class HUBDatasetStats():
task (str): Dataset task. Options are 'detect', 'segment', 'pose', 'classify'. Default is 'detect'.
autodownload (bool): Attempt to download dataset if not found locally. Default is False.
Usage
Example:
```python
from ultralytics.data.utils import HUBDatasetStats
stats = HUBDatasetStats('/Users/glennjocher/Downloads/coco8.zip', task='detect') # detect dataset
stats = HUBDatasetStats('/Users/glennjocher/Downloads/coco8-seg.zip', task='segment') # segment dataset
stats = HUBDatasetStats('/Users/glennjocher/Downloads/coco8-pose.zip', task='pose') # pose dataset
stats = HUBDatasetStats('path/to/coco8.zip', task='detect') # detect dataset
stats = HUBDatasetStats('path/to/coco8-seg.zip', task='segment') # segment dataset
stats = HUBDatasetStats('path/to/coco8-pose.zip', task='pose') # pose dataset
stats.get_json(save=False)
stats.process_images()
```
"""
def __init__(self, path='coco128.yaml', task='detect', autodownload=False):
@ -459,11 +459,14 @@ def compress_one_image(f, f_new=None, max_dim=1920, quality=50):
max_dim (int, optional): The maximum dimension (width or height) of the output image. Default is 1920 pixels.
quality (int, optional): The image compression quality as a percentage. Default is 50%.
Usage:
Example:
```python
from pathlib import Path
from ultralytics.data.utils import compress_one_image
for f in Path('/Users/glennjocher/Downloads/dataset').rglob('*.jpg'):
for f in Path('path/to/dataset').rglob('*.jpg'):
compress_one_image(f)
```
"""
try: # use PIL
im = Image.open(f)
@ -488,9 +491,12 @@ def delete_dsstore(path):
Args:
path (str, optional): The directory path where the ".DS_store" files should be deleted.
Usage:
Example:
```python
from ultralytics.data.utils import delete_dsstore
delete_dsstore('/Users/glennjocher/Downloads/dataset')
delete_dsstore('path/to/dir')
```
Note:
".DS_store" files are created by the Apple operating system and contain metadata about folders and files. They
@ -505,17 +511,18 @@ def delete_dsstore(path):
def zip_directory(dir, use_zipfile_library=True):
"""
Zips a directory and saves the archive to the specified output path.
Zips a directory and saves the archive to the specified output path. Equivalent to 'zip -r coco8.zip coco8/'
Args:
dir (str): The path to the directory to be zipped.
use_zipfile_library (bool): Whether to use zipfile library or shutil for zipping.
Usage:
Example:
```python
from ultralytics.data.utils import zip_directory
zip_directory('/Users/glennjocher/Downloads/playground')
zip -r coco8-pose.zip coco8-pose
zip_directory('/path/to/dir')
```
"""
delete_dsstore(dir)
if use_zipfile_library:
@ -538,9 +545,12 @@ def autosplit(path=DATASETS_DIR / 'coco128/images', weights=(0.9, 0.1, 0.0), ann
weights (list | tuple, optional): Train, validation, and test split fractions. Defaults to (0.9, 0.1, 0.0).
annotated_only (bool, optional): If True, only images with an associated txt file are used. Defaults to False.
Usage:
from utils.dataloaders import autosplit
Example:
```python
from ultralytics.utils.dataloaders import autosplit
autosplit()
```
"""
path = Path(path) # images dir