Spaces:
Runtime error
Runtime error
File size: 3,818 Bytes
f549064 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 |
# Copyright (c) OpenMMLab. All rights reserved.
from typing import Optional, Union
from mmengine.logging import MMLogger
from mmcls.registry import DATASETS
from .categories import IMAGENET_CATEGORIES
from .custom import CustomDataset
@DATASETS.register_module()
class ImageNet(CustomDataset):
"""`ImageNet <http://www.image-net.org>`_ Dataset.
The dataset supports two kinds of annotation format. More details can be
found in :class:`CustomDataset`.
Args:
ann_file (str): Annotation file path. Defaults to ''.
metainfo (dict, optional): Meta information for dataset, such as class
information. Defaults to None.
data_root (str): The root directory for ``data_prefix`` and
``ann_file``. Defaults to ''.
data_prefix (str | dict): Prefix for training data. Defaults to ''.
**kwargs: Other keyword arguments in :class:`CustomDataset` and
:class:`BaseDataset`.
""" # noqa: E501
IMG_EXTENSIONS = ('.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif')
METAINFO = {'classes': IMAGENET_CATEGORIES}
def __init__(self,
ann_file: str = '',
metainfo: Optional[dict] = None,
data_root: str = '',
data_prefix: Union[str, dict] = '',
**kwargs):
kwargs = {'extensions': self.IMG_EXTENSIONS, **kwargs}
super().__init__(
ann_file=ann_file,
metainfo=metainfo,
data_root=data_root,
data_prefix=data_prefix,
**kwargs)
@DATASETS.register_module()
class ImageNet21k(CustomDataset):
"""ImageNet21k Dataset.
Since the dataset ImageNet21k is extremely big, cantains 21k+ classes
and 1.4B files. We won't provide the default categories list. Please
specify it from the ``classes`` argument.
Args:
ann_file (str): Annotation file path. Defaults to ''.
metainfo (dict, optional): Meta information for dataset, such as class
information. Defaults to None.
data_root (str): The root directory for ``data_prefix`` and
``ann_file``. Defaults to ''.
data_prefix (str | dict): Prefix for training data. Defaults to ''.
multi_label (bool): Not implement by now. Use multi label or not.
Defaults to False.
**kwargs: Other keyword arguments in :class:`CustomDataset` and
:class:`BaseDataset`.
"""
IMG_EXTENSIONS = ('.jpg', '.jpeg', '.png', '.ppm', '.bmp', '.pgm', '.tif')
def __init__(self,
ann_file: str = '',
metainfo: Optional[dict] = None,
data_root: str = '',
data_prefix: Union[str, dict] = '',
multi_label: bool = False,
**kwargs):
if multi_label:
raise NotImplementedError(
'The `multi_label` option is not supported by now.')
self.multi_label = multi_label
logger = MMLogger.get_current_instance()
if not ann_file:
logger.warning(
'The ImageNet21k dataset is large, and scanning directory may '
'consume long time. Considering to specify the `ann_file` to '
'accelerate the initialization.')
kwargs = {'extensions': self.IMG_EXTENSIONS, **kwargs}
super().__init__(
ann_file=ann_file,
metainfo=metainfo,
data_root=data_root,
data_prefix=data_prefix,
**kwargs)
if self.CLASSES is None:
logger.warning(
'The CLASSES is not stored in the `ImageNet21k` class. '
'Considering to specify the `classes` argument if you need '
'do inference on the ImageNet-21k dataset')
|