编写自定义数据集

使用集合让一切井井有条 根据您的偏好保存内容并对其进行分类。

cd path/to/my/project/datasets/
tfds new my_dataset  # Create `my_dataset/my_dataset.py` template files
# [...] Manually modify `my_dataset/my_dataset_dataset_builder.py` to implement your dataset.
cd my_dataset/
tfds build  # Download and prepare the dataset to `~/tensorflow_datasets/`

import my.project.datasets.my_dataset  # Register `my_dataset`

ds = tfds.load('my_dataset')  # `my_dataset` registered

cd path/to/project/datasets/  # Or use `--dir=path/to/project/datasets/` below
tfds new my_dataset

my_dataset/
    __init__.py
    README.md # Markdown description of the dataset.
    CITATIONS.bib # Bibtex citation for the dataset.
    TAGS.txt # List of tags describing the dataset.
    my_dataset_dataset_builder.py # Dataset definition
    my_dataset_dataset_builder_test.py # Test
    dummy_data/ # (optional) Fake data (used for testing)
    checksum.tsv # (optional) URL checksums (see `checksums` section).

class Builder(tfds.core.GeneratorBasedBuilder):
  """DatasetBuilder for my_dataset dataset."""

  VERSION = tfds.core.Version('1.0.0')
  RELEASE_NOTES = {
      '1.0.0': 'Initial release.',
  }

  def _info(self) -> tfds.core.DatasetInfo:
    """Dataset metadata (homepage, citation,...)."""
    return self.dataset_info_from_configs(
        features=tfds.features.FeaturesDict({
            'image': tfds.features.Image(shape=(256, 256, 3)),
            'label': tfds.features.ClassLabel(
                names=['no', 'yes'],
                doc='Whether this is a picture of a cat'),
        }),
    )

  def _split_generators(self, dl_manager: tfds.download.DownloadManager):
    """Download the data and define splits."""
    extracted_path = dl_manager.download_and_extract('http://data.org/data.zip')
    # dl_manager returns pathlib-like objects with `path.read_text()`,
    # `path.iterdir()`,...
    return {
        'train': self._generate_examples(path=extracted_path / 'train_images'),
        'test': self._generate_examples(path=extracted_path / 'test_images'),
    }

  def _generate_examples(self, path) -> Iterator[Tuple[Key, Example]]:
    """Generator of examples for each split."""
    for img_path in path.glob('*.jpeg'):
      # Yields (key, example)
      yield img_path.name, {
          'image': img_path,
          'label': 'yes' if img_path.name.startswith('yes_') else 'no',
      }

def _info(self):
  # The `dataset_info_from_configs` base method will construct the
  # `tfds.core.DatasetInfo` object using the passed-in parameters and
  # adding: builder (self), description/citations/tags from the config
  # files located in the same package.
  return self.dataset_info_from_configs(
      homepage='https://dataset-homepage.org',
      features=tfds.features.FeaturesDict({
          'image_description': tfds.features.Text(),
          'image': tfds.features.Image(),
          # Here, 'label' can be 0-4.
          'label': tfds.features.ClassLabel(num_classes=5),
      }),
      # If there's a common `(input, target)` tuple from the features,
      # specify them here. They'll be used if as_supervised=True in
      # builder.as_dataset.
      supervised_keys=('image', 'label'),
      # Specify whether to disable shuffling on the examples. Set to False by default.
      disable_shuffling=False,
  )

def _info(self):
  return self.dataset_info_from_configs(
    # [...]
    disable_shuffling=True,
    # [...]
  )

extracted_paths = dl_manager.download_and_extract({
    'foo': 'https://example.com/foo.zip',
    'bar': 'https://example.com/bar.zip',
})
# This returns:
assert extracted_paths == {
    'foo': Path('/path/to/extracted_foo/'),
    'bar': Path('/path/extracted_bar/'),
}

class MyDataset(tfds.core.GeneratorBasedBuilder):

  MANUAL_DOWNLOAD_INSTRUCTIONS = """
  Register into https://example.org/login to get the data. Place the `data.zip`
  file in the `manual_dir/`.
  """

  def _split_generators(self, dl_manager):
    # data_path is a pathlib-like `Path('<manual_dir>/data.zip')`
    archive_path = dl_manager.manual_dir / 'data.zip'
    # Extract the manually downloaded `data.zip`
    extracted_path = dl_manager.extract(archive_path)
    ...

for filename, fobj in dl_manager.iter_archive('path/to/archive.zip'):
  ...

def _split_generators(self, dl_manager):
  # Download source data
  extracted_path = dl_manager.download_and_extract(...)

  # Specify the splits
  return {
      'train': self._generate_examples(
          images_path=extracted_path / 'train_imgs',
          label_path=extracted_path / 'train_labels.csv',
      ),
      'test': self._generate_examples(
          images_path=extracted_path / 'test_imgs',
          label_path=extracted_path / 'test_labels.csv',
      ),
  }

def _generate_examples(self, images_path, label_path):
  # Read the input data out of the source files
  with label_path.open() as f:
    for row in csv.DictReader(f):
      image_id = row['image_id']
      # And yield (key, feature_dict)
      yield image_id, {
          'image_description': row['description'],
          'image': images_path / f'{image_id}.jpeg',
          'label': row['label'],
      }

path = dl_manager.download_and_extract('http://some-website/my_data.zip')

json_path = path / 'data/file.json'

json.loads(json_path.read_text())

import my_project.datasets.my_dataset  # Register MyDataset

ds = tfds.load('my_dataset')  # MyDataset available

cd path/to/datasets/my_dataset/
tfds build --register_checksums

import tensorflow_datasets as tfds
from . import my_dataset_dataset_builder


class MyDatasetTest(tfds.testing.DatasetBuilderTestCase):
  """Tests for my_dataset dataset."""
  DATASET_CLASS = my_dataset_dataset_builder.Builder
  SPLITS = {
      'train': 3,  # Number of fake train example
      'test': 1,  # Number of fake test example
  }

  # If you are calling `download/download_and_extract` with a dict, like:
  #   dl_manager.download({'some_key': 'http://a.org/out.txt', ...})
  # then the tests needs to provide the fake output paths relative to the
  # fake data directory
  DL_EXTRACT_RESULT = {
      'name1': 'path/to/file1',  # Relative to my_dataset/dummy_data dir.
      'name2': 'file2',
  }


if __name__ == '__main__':
  tfds.testing.test_main()

python my_dataset_test.py