def _parse_dataset_info_proto(
self, config_name: str,
config: Mapping[str, Any]) -> dataset_info_pb2.DatasetInfo:
"""Parses a DatasetInfo proto from the given Json."""
splits = []
for name, details in config['splits'].items():
splits.append(
dataset_info_pb2.SplitInfo(
name=name,
num_shards=1,
shard_lengths=[details['num_examples']],
num_bytes=details['num_bytes']))
if isinstance(config['version'], dict):
version = config['version']['version_str']
elif isinstance(config['version'], str):
version = config['version']
return dataset_info_pb2.DatasetInfo(
name=config_name,
module_name=config_name,
description=config['description'],
version=version,
citation=config['citation'],
redistribution_info=dataset_info_pb2.RedistributionInfo(
license=config['license']),
splits=splits,
features=_get_huggingface_features(config),
)
def __init__(self,
builder,
description=None,
features=None,
supervised_keys=None,
urls=None,
citation=None,
metadata=None,
redistribution_info=None):
"""Constructs DatasetInfo.
Args:
builder: `DatasetBuilder`, dataset builder for this info.
description: `str`, description of this dataset.
features: `tfds.features.FeaturesDict`, Information on the feature dict
of the `tf.data.Dataset()` object from the `builder.as_dataset()`
method.
supervised_keys: `tuple`, Specifies the input feature and the label for
supervised learning, if applicable for the dataset.
urls: `list(str)`, optional, the homepage(s) for this dataset.
citation: `str`, optional, the citation to use for this dataset.
metadata: `tfds.core.Metadata`, additonal object which will be
stored/restored with the dataset. This allows for storing additional
information with the dataset.
redistribution_info: `dict`, optional, information needed for
redistribution, as specified in `dataset_info_pb2.RedistributionInfo`.
The content of the `license` subfield will automatically be written to a
LICENSE file stored with the dataset.
"""
self._builder = builder
self._info_proto = dataset_info_pb2.DatasetInfo(
name=builder.name,
description=description,
version=str(builder._version), # pylint: disable=protected-access
citation=citation,
redistribution_info=dataset_info_pb2.RedistributionInfo(
**redistribution_info) if redistribution_info else None)
if urls:
self._info_proto.location.urls[:] = urls
self._features = features
self._splits = splits_lib.SplitDict()
if supervised_keys is not None:
assert isinstance(supervised_keys, tuple)
assert len(supervised_keys) == 2
self._info_proto.supervised_keys.input = supervised_keys[0]
self._info_proto.supervised_keys.output = supervised_keys[1]
if metadata and not isinstance(metadata, Metadata):
raise ValueError(
"Metadata should be a `tfds.core.Metadata` instance. Received "
"{}".format(metadata))
self._metadata = metadata
# Is this object initialized with both the static and the dynamic data?
self._fully_initialized = False
def __init__(self,
builder,
description=None,
features=None,
supervised_keys=None,
homepage=None,
citation=None,
metadata=None,
redistribution_info=None):
"""Constructs DatasetInfo.
Args:
builder: `DatasetBuilder`, dataset builder for this info.
description: `str`, description of this dataset.
features: `tfds.features.FeaturesDict`, Information on the feature dict
of the `tf.data.Dataset()` object from the `builder.as_dataset()`
method.
supervised_keys: `tuple` of `(input_key, target_key)`, Specifies the
input feature and the label for supervised learning, if applicable for
the dataset. The keys correspond to the feature names to select in
`info.features`. When calling `tfds.core.DatasetBuilder.as_dataset()`
with `as_supervised=True`, the `tf.data.Dataset` object will yield
the (input, target) defined here.
homepage: `str`, optional, the homepage for this dataset.
citation: `str`, optional, the citation to use for this dataset.
metadata: `tfds.core.Metadata`, additonal object which will be
stored/restored with the dataset. This allows for storing additional
information with the dataset.
redistribution_info: `dict`, optional, information needed for
redistribution, as specified in `dataset_info_pb2.RedistributionInfo`.
The content of the `license` subfield will automatically be written to a
LICENSE file stored with the dataset.
"""
self._builder = builder
self._info_proto = dataset_info_pb2.DatasetInfo(
name=builder.name,
description=utils.dedent(description),
version=str(builder._version), # pylint: disable=protected-access
citation=utils.dedent(citation),
redistribution_info=dataset_info_pb2.RedistributionInfo(
license=utils.dedent(redistribution_info.pop("license")),
**redistribution_info) if redistribution_info else None)
if homepage:
self._info_proto.location.urls[:] = [homepage]
if features:
if not isinstance(features, top_level_feature.TopLevelFeature):
raise ValueError(
"DatasetInfo.features only supports FeaturesDict or Sequence at "
"the top-level. Got {}".format(features))
features._set_top_level() # pylint: disable=protected-access
self._features = features
self._splits = splits_lib.SplitDict(self._builder.name)
if supervised_keys is not None:
assert isinstance(supervised_keys, tuple)
assert len(supervised_keys) == 2
self._info_proto.supervised_keys.input = supervised_keys[0]
self._info_proto.supervised_keys.output = supervised_keys[1]
if metadata and not isinstance(metadata, Metadata):
raise ValueError(
"Metadata should be a `tfds.core.Metadata` instance. Received "
"{}".format(metadata))
self._metadata = metadata
# Is this object initialized with both the static and the dynamic data?
self._fully_initialized = False
def __init__(
self,
*,
builder: Union[DatasetIdentity, Any],
description: Optional[str] = None,
features: Optional[feature_lib.FeatureConnector] = None,
supervised_keys: Optional[SupervisedKeysType] = None,
disable_shuffling: bool = False,
homepage: Optional[str] = None,
citation: Optional[str] = None,
metadata: Optional[Metadata] = None,
license: Optional[str] = None, # pylint: disable=redefined-builtin
redistribution_info: Optional[Dict[str, str]] = None,
split_dict: Optional[splits_lib.SplitDict] = None):
# pyformat: disable
"""Constructs DatasetInfo.
Args:
builder: `DatasetBuilder` or `DatasetIdentity`. The dataset builder or
identity will be used to populate this info.
description: `str`, description of this dataset.
features: `tfds.features.FeaturesDict`, Information on the feature dict of
the `tf.data.Dataset()` object from the `builder.as_dataset()` method.
supervised_keys: Specifies the input structure for supervised learning, if
applicable for the dataset, used with "as_supervised". The keys
correspond to the feature names to select in `info.features`. When
calling `tfds.core.DatasetBuilder.as_dataset()` with
`as_supervised=True`, the `tf.data.Dataset` object will yield the
structure defined by the keys passed here, instead of that defined by
the `features` argument. Typically this is a `(input_key, target_key)`
tuple, and the dataset yields a tuple of tensors `(input, target)`
tensors.
To yield a more complex structure, pass a tuple of `tf.nest` compatible
structures of feature keys. The resulting `Dataset` will yield
structures with each key replaced by the coresponding tensor. For
example, passing a triple of keys would return a dataset
that yields `(feature, target, sample_weights)` triples for keras.
Using `supervised_keys=({'a':'a','b':'b'}, 'c')` would create a dataset
yielding a tuple with a dictionary of features in the `features`
position.
Note that selecting features in nested `tfds.features.FeaturesDict`
objects is not supported.
disable_shuffling: `bool`, specify whether to shuffle the examples.
homepage: `str`, optional, the homepage for this dataset.
citation: `str`, optional, the citation to use for this dataset.
metadata: `tfds.core.Metadata`, additonal object which will be
stored/restored with the dataset. This allows for storing additional
information with the dataset.
license: license of the dataset.
redistribution_info: information needed for redistribution, as specified
in `dataset_info_pb2.RedistributionInfo`. The content of the `license`
subfield will automatically be written to a LICENSE file stored with the
dataset.
split_dict: information about the splits in this dataset.
"""
# pyformat: enable
self._builder_or_identity = builder
if isinstance(builder, DatasetIdentity):
self._identity = builder
else:
self._identity = DatasetIdentity.from_builder(builder)
self._info_proto = dataset_info_pb2.DatasetInfo(
name=self._identity.name,
description=utils.dedent(description),
version=str(self._identity.version),
release_notes=self._identity.release_notes,
disable_shuffling=disable_shuffling,
config_name=self._identity.config_name,
config_description=self._identity.config_description,
citation=utils.dedent(citation),
module_name=self._identity.module_name,
redistribution_info=dataset_info_pb2.RedistributionInfo(
license=utils.dedent(license
or redistribution_info.pop("license")),
**redistribution_info) if redistribution_info else None)
if homepage:
self._info_proto.location.urls[:] = [homepage]
if features:
if not isinstance(features, top_level_feature.TopLevelFeature):
raise ValueError(
"DatasetInfo.features only supports FeaturesDict or Sequence at "
"the top-level. Got {}".format(features))
self._features = features
self._splits = splits_lib.SplitDict([])
if split_dict:
self.set_splits(split_dict)
if supervised_keys is not None:
self._info_proto.supervised_keys.CopyFrom(
_supervised_keys_to_proto(supervised_keys))
if metadata and not isinstance(metadata, Metadata):
raise ValueError(
"Metadata should be a `tfds.core.Metadata` instance. Received "
"{}".format(metadata))
self._metadata = metadata
# Is this object initialized with both the static and the dynamic data?
self._fully_initialized = False
