easycv.datasets.selfsup.data_sources package

class easycv.datasets.selfsup.data_sources.SSLSourceImageList(list_file, root='', max_try=20)

Bases: object

datasource for classification

Parameters

• list_file – str / list(str), str means a input image list file path, this file contains records as image_path label in list_file list(str) means multi image list, each one contains some records as image_path label

• root – str / list(str), root path for image_path, each list_file will need a root, if len(root) < len(list_file), we will use root[-1] to fill root list.

• max_try – int, max try numbers of reading image

__init__(list_file, root='', max_try=20)

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

static parse_list_file(list_file, root)

class easycv.datasets.selfsup.data_sources.SSLSourceImageNetFeature(root_path, training=True, data_keyword='feat1', label_keyword='label', dynamic_load=True)

Bases: object

__init__(root_path, training=True, data_keyword='feat1', label_keyword='label', dynamic_load=True)

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

Submodules

easycv.datasets.selfsup.data_sources.image_list module

class easycv.datasets.selfsup.data_sources.image_list.SSLSourceImageList(list_file, root='', max_try=20)

Bases: object

datasource for classification

Parameters

• list_file – str / list(str), str means a input image list file path, this file contains records as image_path label in list_file list(str) means multi image list, each one contains some records as image_path label

• root – str / list(str), root path for image_path, each list_file will need a root, if len(root) < len(list_file), we will use root[-1] to fill root list.

• max_try – int, max try numbers of reading image

__init__(list_file, root='', max_try=20)

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

static parse_list_file(list_file, root)

easycv.datasets.selfsup.data_sources.imagenet_feature module

class easycv.datasets.selfsup.data_sources.imagenet_feature.SSLSourceImageNetFeature(root_path, training=True, data_keyword='feat1', label_keyword='label', dynamic_load=True)

Bases: object

__init__(root_path, training=True, data_keyword='feat1', label_keyword='label', dynamic_load=True)

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