HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.0.79 expand Docs reference section (#2053)

Browse source 
Co-authored-by: Ayush Chaurasia <ayush.chaurarsia@gmail.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Fri3dChicken <87434761+AmoghDhaliwal@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2023-04-16 12:28:12 +02:00 • committed by GitHub
parent 47bd8b433b
commit 31db8ed163
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
106 changed files with 2570 additions and 529 deletions
Download patch file Download diff file Expand all files Collapse all files

23
ultralytics/yolo/data/dataset_wrappers.py
View file

@ -7,21 +7,36 @@ from .augment import LetterBox
class MixAndRectDataset:
"""A wrapper of multiple images mixed dataset.
"""
A dataset class that applies mosaic and mixup transformations as well as rectangular training.
Args:
dataset (:obj:`BaseDataset`): The dataset to be mixed.
transforms (Sequence[dict]): config dict to be composed.
Attributes:
dataset: The base dataset.
imgsz: The size of the images in the dataset.
"""
def __init__(self, dataset):
"""
Args:
dataset (BaseDataset): The base dataset to apply transformations to.
"""
self.dataset = dataset
self.imgsz = dataset.imgsz
def __len__(self):
"""Returns the number of items in the dataset."""
return len(self.dataset)
def __getitem__(self, index):
"""
Applies mosaic, mixup and rectangular training transformations to an item in the dataset.
Args:
index (int): Index of the item in the dataset.
Returns:
(dict): A dictionary containing the transformed item data.
"""
labels = deepcopy(self.dataset[index])
for transform in self.dataset.transforms.tolist():
# mosaic and mixup