# tfg.datasets.pix3d.Pix3d

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/graphics/blob/master/tensorflow_graphics/datasets/pix3d/pix3d.py#L83-L289) |

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

    tfg.datasets.pix3d.Pix3d(
        *, file_format: Union[None, str, file_adapters.FileFormat] = None, **kwargs
    )

<br />

<br />

<br />

| ## Args ||
|---|---|
| `file_format` | EXPERIMENTAL, may change at any time; Format of the record files in which dataset will be read/written to. If `None`, defaults to `tfrecord`. |
| `**kwargs` | Arguments passed to `DatasetBuilder`. |

<br />

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `builder_config` | [`tfds.core.BuilderConfig`](https://www.tensorflow.org/datasets/api_docs/python/tfds/core/BuilderConfig) for this builder. |
| `canonical_version` | <br /> <br /> |
| `data_dir` | <br /> <br /> |
| `data_path` | <br /> <br /> |
| `info` | [`tfds.core.DatasetInfo`](https://www.tensorflow.org/datasets/api_docs/python/tfds/core/DatasetInfo) for this builder. |
| `release_notes` | <br /> <br /> |
| `supported_versions` | <br /> <br /> |
| `version` | <br /> <br /> |
| `versions` | Versions (canonical + availables), in preference order. |

<br />

## Methods

### `as_dataset`

    as_dataset(
        split: Optional[Tree[splits_lib.SplitArg]] = None,
        *,
        batch_size: Optional[int] = None,
        shuffle_files: bool = False,
        decoders: Optional[TreeDict[decode.partial_decode.DecoderArg]] = None,
        read_config: Optional[read_config_lib.ReadConfig] = None,
        as_supervised: bool = False
    )

Constructs a [`tf.data.Dataset`](https://www.tensorflow.org/api_docs/python/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>)

<br />

<br />

<br />

| Args ||
|---|---|
| `split` | Which split of the data to load (e.g. `'train'`, `'test'`, `['train', 'test']`, `'train[80%:]'`,...). See our [split API guide](https://www.tensorflow.org/datasets/splits). If `None`, will return all splits in a `Dict[Split, 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`](https://www.tensorflow.org/api_docs/python/tf/data) API to construct a custom pipeline. If `batch_size == -1`, will return feature dictionaries of the whole dataset with [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor)s instead of a [`tf.data.Dataset`](https://www.tensorflow.org/api_docs/python/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](https://github.com/tensorflow/datasets/blob/master/docs/decode.md) for more info. |
| `read_config` | [`tfds.ReadConfig`](https://www.tensorflow.org/datasets/api_docs/python/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`](https://www.tensorflow.org/api_docs/python/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`](https://www.tensorflow.org/api_docs/python/tf/data/Dataset) will have a dictionary with all the features. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| [`tf.data.Dataset`](https://www.tensorflow.org/api_docs/python/tf/data/Dataset), or if `split=None`, `dict<key: tfds.Split, value: tf.data.Dataset>`. <br /> If `batch_size` is -1, will return feature dictionaries containing the entire dataset in [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor)s instead of a [`tf.data.Dataset`](https://www.tensorflow.org/api_docs/python/tf/data/Dataset). ||

<br />

### `dataset_info_from_configs`

    dataset_info_from_configs(
        **kwargs
    )

Returns the DatasetInfo using given kwargs and config files.

Sub-class should call this and add information not present in config files
using kwargs directly passed to tfds.core.DatasetInfo object.

If information is present both in passed arguments and config files, config
files will prevail.

<br />

<br />

<br />

| Args ||
|---|---|
| `**kwargs` | kw args to pass to DatasetInfo directly. |

<br />

### `download_and_prepare`

    download_and_prepare(
        *,
        download_dir: Optional[epath.PathLike] = None,
        download_config: Optional[download.DownloadConfig] = None,
        file_format: Optional[Union[str, file_adapters.FileFormat]] = None
    ) -> None

Downloads and prepares dataset for reading.

<br />

<br />

<br />

| Args ||
|---|---|
| `download_dir` | directory where downloaded files are stored. Defaults to "\~/tensorflow-datasets/downloads". |
| `download_config` | [`tfds.download.DownloadConfig`](https://www.tensorflow.org/datasets/api_docs/python/tfds/download/DownloadConfig), further configuration for downloading and preparing dataset. |
| `file_format` | optional `str` or `file_adapters.FileFormat`, format of the record files in which the dataset will be written. |

<br />

<br />

<br />

<br />

| Raises ||
|---|---|
| `IOError` | if there is not enough disk space available. |
| `RuntimeError` | when the config cannot be found. |

<br />

### `get_default_builder_config`

    get_default_builder_config() -> Optional[BuilderConfig]

Returns the default builder config if there is one.

Note that for dataset builders that cannot use the `cls.BUILDER_CONFIGS`, we
need a method that uses the instance to get `BUILDER_CONFIGS` and
`DEFAULT_BUILDER_CONFIG_NAME`.

<br />

<br />

<br />

| Returns ||
|---|---|
| the default builder config if there is one ||

<br />

### `get_metadata`

    @classmethod
    get_metadata() -> dataset_metadata.DatasetMetadata

Returns metadata (README, CITATIONS, ...) specified in config files.

The config files are read from the same package where the DatasetBuilder has
been defined, so those metadata might be wrong for legacy builders.

### `get_reference`

    get_reference(
        namespace: Optional[str] = None
    ) -> naming.DatasetReference

Returns a reference to the dataset produced by this dataset builder.

Includes the config if specified, the version, and the data_dir that should
contain this dataset.

<br />

<br />

<br />

| Arguments ||
|---|---|
| `namespace` | if this dataset is a community dataset, and therefore has a namespace, then the namespace must be provided such that it can be set in the reference. Note that a dataset builder is not aware that it is part of a namespace. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| a reference to this instantiated builder. ||

<br />

<br />

<br />

<br />

| ## Class Variables ||
|---|---|
| BUILDER_CONFIGS | `[]` |
| CLASS_INDEX | `['background', 'bed', 'bookcase', 'chair', 'desk', 'misc', 'sofa', 'table', 'tool', 'wardrobe']` |
| DEFAULT_BUILDER_CONFIG_NAME | `None` |
| MANUAL_DOWNLOAD_INSTRUCTIONS | `None` |
| MAX_SIMULTANEOUS_DOWNLOADS | `None` |
| RELEASE_NOTES | <br /> { } <br /> |
| SUPPORTED_VERSIONS | `[]` |
| TEST_SPLIT_IDX | `'/tmpfs/venv/lib/python3.9/site-packages/tensorflow_graphics/datasets/pix3d/splits/pix3d_test.npy'` |
| TRAIN_SPLIT_IDX | `'/tmpfs/venv/lib/python3.9/site-packages/tensorflow_graphics/datasets/pix3d/splits/pix3d_train.npy'` |
| VERSION | Instance of `tensorflow_datasets.core.utils.version.Version` |
| builder_config_cls | `None` |
| builder_configs | <br /> { } <br /> |
| code_path | Instance of `etils.epath.gpath.PosixGPath` |
| default_builder_config | `None` |
| name | `'pix3d'` |
| pkg_dir_path | `None` |
| url_infos | `None` |

<br />