easycv.datasets.selfsup.pipelines package

class easycv.datasets.selfsup.pipelines.RandomAppliedTrans(transforms, p=0.5)

Bases: object

Randomly applied transformations. :param transforms: List of transformations in dictionaries. :type transforms: List[Dict]

__init__(transforms, p=0.5)

Initialize self. See help(type(self)) for accurate signature.

class easycv.datasets.selfsup.pipelines.Lighting

Bases: object

Lighting noise(AlexNet - style PCA - based noise)

__init__()

Initialize self. See help(type(self)) for accurate signature.

class easycv.datasets.selfsup.pipelines.Solarization(threshold=128)

Bases: object

__init__(threshold=128)

Initialize self. See help(type(self)) for accurate signature.

Submodules

easycv.datasets.selfsup.pipelines.transforms module

class easycv.datasets.selfsup.pipelines.transforms.MAEFtAugment(input_size=None, color_jitter=None, auto_augment=None, interpolation=None, re_prob=None, re_mode=None, re_count=None, mean=None, std=None, is_train=True)

Bases: object

RandAugment data augmentation method based on “RandAugment: Practical automated data augmentation with a reduced search space”. This code is borrowed from <https://github.com/pengzhiliang/MAE-pytorch> :param input_size: images input size :type input_size: int :param color_jitter: Color jitter factor :type color_jitter: float :param auto_augment: Use AutoAugment policy :param iterpolation: Training interpolation :param re_prob: Random erase prob :param re_mode: Random erase mode :param re_count: Random erase count :param mean: mean used for normalization :param std: std used for normalization :param is_train: If True use all augmentation strategy

__init__(input_size=None, color_jitter=None, auto_augment=None, interpolation=None, re_prob=None, re_mode=None, re_count=None, mean=None, std=None, is_train=True)

Initialize self. See help(type(self)) for accurate signature.

class easycv.datasets.selfsup.pipelines.transforms.RandomAppliedTrans(transforms, p=0.5)

Bases: object

Randomly applied transformations. :param transforms: List of transformations in dictionaries. :type transforms: List[Dict]

__init__(transforms, p=0.5)

Initialize self. See help(type(self)) for accurate signature.

class easycv.datasets.selfsup.pipelines.transforms.Lighting

Bases: object

Lighting noise(AlexNet - style PCA - based noise)

__init__()

Initialize self. See help(type(self)) for accurate signature.

class easycv.datasets.selfsup.pipelines.transforms.Solarization(threshold=128)

Bases: object

__init__(threshold=128)

Initialize self. See help(type(self)) for accurate signature.