Shortcuts

mmedit.datasets.cifar10_dataset

Module Contents

Classes

CIFAR10

CIFAR10 Dataset.

class mmedit.datasets.cifar10_dataset.CIFAR10(data_prefix: str, test_mode: bool, metainfo: Optional[dict] = None, data_root: str = '', download: bool = True, **kwargs)[源代码]

Bases: mmedit.datasets.basic_conditional_dataset.BasicConditionalDataset

CIFAR10 Dataset.

This implementation is modified from https://github.com/pytorch/vision/blob/master/torchvision/datasets/cifar.py

参数
  • data_prefix (str) – Prefix for data.

  • test_mode (bool) – test_mode=True means in test phase. It determines to use the training set or test set.

  • metainfo (dict, optional) – Meta information for dataset, such as categories information. Defaults to None.

  • data_root (str) – The root directory for data_prefix. Defaults to ‘’.

  • download (bool) – Whether to download the dataset if not exists. Defaults to True.

  • **kwargs – Other keyword arguments in BaseDataset.

base_folder = 'cifar-10-batches-py'[源代码]
url = 'https://www.cs.toronto.edu/~kriz/cifar-10-python.tar.gz'[源代码]
filename = 'cifar-10-python.tar.gz'[源代码]
tgz_md5 = 'c58f30108f718f92721af3b95e74349a'[源代码]
train_list = [['data_batch_1', 'c99cafc152244af753f735de768cd75f'], ['data_batch_2',...[源代码]
test_list = [['test_batch', '40351d587109b95175f43aff81a1287e']][源代码]
meta[源代码]
METAINFO[源代码]
load_data_list()[源代码]

Load images and ground truth labels.

_load_meta()[源代码]

Load categories information from metafile.

_check_integrity()[源代码]

Check the integrity of data files.

extra_repr() List[str][源代码]

The extra repr information of the dataset.

Read the Docs v: latest
Versions
master
latest
stable
zyh-doc-notfound-extend
Downloads
pdf
epub
On Read the Docs
Project Home
Builds

Free document hosting provided by Read the Docs.