tfg.datasets.pix3d.Pix3d

Pix3D is a large-scale dataset of diverse image-shape pairs with pixel-level 2D-3D alignment.

tfg.datasets.pix3d.Pix3d(
    data_dir=None, config=None, version=None
)

data_dir str, directory to read/write data. Defaults to "~/tensorflow_datasets".
config tfds.core.BuilderConfig or str name, optional configuration for the dataset that affects the data generated on disk. Different builder_configs will have their own subdirectories and versions.
version str. Optional version at which to load the dataset. An error is raised if specified version cannot be satisfied. Eg: '1.2.3', '1.2.*'. The special value "experimental_latest" will use the highest version, even if not default. This is not recommended unless you know what you are doing, as the version could be broken.

builder_config tfds.core.BuilderConfig for this builder.
canonical_version

data_dir

info tfds.core.DatasetInfo for this builder.
supported_versions

version

versions Versions (canonical + availables), in preference order.

Methods

as_dataset

as_dataset(
    split=None, batch_size=None, shuffle_files=False, decoders=None,
    read_config=None, as_supervised=False, in_memory=None
)

Constructs a tf.data.Dataset.

Callers must pass arguments as keyword arguments.

The output types vary depending on the parameters. Examples:

builder = tfds.builder('imdb_reviews')
builder.download_and_prepare()

# Default parameters: Returns the dict of tf.data.Dataset
ds_all_dict = builder.as_dataset()
assert isinstance(ds_all_dict, dict)
print(ds_all_dict.keys())  # ==> ['test', 'train', 'unsupervised']

assert isinstance(ds_all_dict['test'], tf.data.Dataset)
# Each dataset (test, train, unsup.) consists of dictionaries
# {'label': <tf.Tensor: .. dtype=int64, numpy=1>,
#  'text': <tf.Tensor: .. dtype=string, numpy=b"I've watched the movie ..">}
# {'label': <tf.Tensor: .. dtype=int64, numpy=1>,
#  'text': <tf.Tensor: .. dtype=string, numpy=b'If you love Japanese ..'>}

# With as_supervised: tf.data.Dataset only contains (feature, label) tuples
ds_all_supervised = builder.as_dataset(as_supervised=True)
assert isinstance(ds_all_supervised, dict)
print(ds_all_supervised.keys())  # ==> ['test', 'train', 'unsupervised']

assert isinstance(ds_all_supervised['test'], tf.data.Dataset)
# Each dataset (test, train, unsup.) consists of tuples (text, label)
# (<tf.Tensor: ... dtype=string, numpy=b"I've watched the movie ..">,
#  <tf.Tensor: ... dtype=int64, numpy=1>)
# (<tf.Tensor: ... dtype=string, numpy=b"If you love Japanese ..">,
#  <tf.Tensor: ... dtype=int64, numpy=1>)

# Same as above plus requesting a particular split
ds_test_supervised = builder.as_dataset(as_supervised=True, split='test')
assert isinstance(ds_test_supervised, tf.data.Dataset)
# The dataset consists of tuples (text, label)
# (<tf.Tensor: ... dtype=string, numpy=b"I've watched the movie ..">,
#  <tf.Tensor: ... dtype=int64, numpy=1>)
# (<tf.Tensor: ... dtype=string, numpy=b"If you love Japanese ..">,
#  <tf.Tensor: ... dtype=int64, numpy=1>)

Args
split tfds.core.SplitBase, which subset(s) of the data to read. If None (default), returns all splits in a dict <key: tfds.Split, value: tf.data.Dataset>.
batch_size int, batch size. Note that variable-length features will be 0-padded if batch_size is set. Users that want more custom behavior should use batch_size=None and use the tf.data API to construct a custom pipeline. If batch_size == -1, will return feature dictionaries of the whole dataset with tf.Tensors instead of a tf.data.Dataset.
shuffle_files bool, whether to shuffle the input files. Defaults to False.
decoders Nested dict of Decoder objects which allow to customize the decoding. The structure should match the feature structure, but only customized feature keys need to be present. See the guide for more info.
read_config tfds.ReadConfig, Additional options to configure the input pipeline (e.g. seed, num parallel reads,...).
as_supervised bool, if True, the returned tf.data.Dataset will have a 2-tuple structure (input, label) according to builder.info.supervised_keys. If False, the default, the returned tf.data.Dataset will have a dictionary with all the features.
in_memory bool, if True, loads the dataset in memory which increases iteration speeds. Note that if True and the dataset has unknown dimensions, the features will be padded to the maximum size across the dataset.

Returns
tf.data.Dataset, or if split=None, dict<key: tfds.Split, value: tfds.data.Dataset>.

If batch_size is -1, will return feature dictionaries containing the entire dataset in tf.Tensors instead of a tf.data.Dataset.

download_and_prepare

download_and_prepare(
    download_dir=None, download_config=None
)

Downloads and prepares dataset for reading.

Args
download_dir str, directory where downloaded files are stored. Defaults to "~/tensorflow-datasets/downloads".
download_config tfds.download.DownloadConfig, further configuration for downloading and preparing dataset.

Raises
IOError if there is not enough disk space available.

BUILDER_CONFIGS

CLASS_INDEX

IN_DEVELOPMENT False
MANUAL_DOWNLOAD_INSTRUCTIONS None
SUPPORTED_VERSIONS

TEST_SPLIT_IDX '/home/kbuilder/.local/lib/python3.7/site-packages/tensorflow_graphics/datasets/pix3d/splits/pix3d_test.npy'
TRAIN_SPLIT_IDX '/home/kbuilder/.local/lib/python3.7/site-packages/tensorflow_graphics/datasets/pix3d/splits/pix3d_train.npy'
VERSION

builder_configs

name 'pix3d'