Save the date! Google I/O returns May 18-20 Register now

tfg.datasets.features.Pose

FeatureConnector for 3d pose representations.

tfg.datasets.features.Pose()

During _generate_examples, the feature connector accepts as input any of:

  • dict: A dictionary containing the rotation and translation of the object (see output format below).

Output:

A dictionary containing:

  • 'R': A float32 tensor with shape [3, 3] denoting the 3D rotation matrix.
  • 't': A float32 tensor with shape [3,] denoting the translation vector.

feature_dict (dict): Dictionary containing the feature connectors of a example. The keys should correspond to the data dict as returned by tf.data.Dataset(). Types (tf.int32,...) and dicts will automatically be converted into FeatureConnector.

ValueError If one of the given features is not recognized

dtype Return the dtype (or dict of dtype) of this FeatureConnector.
shape Return the shape (or dict of shape) of this FeatureConnector.

Methods

decode_batch_example

decode_batch_example(
    tfexample_data
)

Decode multiple features batched in a single tf.Tensor.

This function is used to decode features wrapped in tfds.features.Sequence(). By default, this function apply decode_example on each individual elements using tf.map_fn. However, for optimization, features can overwrite this method to apply a custom batch decoding.

Args
tfexample_data Same tf.Tensor inputs as decode_example, but with and additional first dimension for the sequence length.

Returns
tensor_data Tensor or dictionary of tensor, output of the tf.data.Dataset object

decode_example

decode_example(
    serialized_example, decoders=None
)

Decode the serialize examples.

Args
serialized_example Nested dict of tf.Tensor
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.

Returns
example Nested dict containing the decoded nested examples.

decode_ragged_example

decode_ragged_example(
    tfexample_data
)

Decode nested features from a tf.RaggedTensor.

This function is used to decode features wrapped in nested tfds.features.Sequence(). By default, this function apply decode_batch_example on the flat values of the ragged tensor. For optimization, features can overwrite this method to apply a custom batch decoding.

Args
tfexample_data tf.RaggedTensor inputs containing the nested encoded examples.

Returns
tensor_data The decoded tf.RaggedTensor or dictionary of tensor, output of the tf.data.Dataset object

encode_example

View source

encode_example(
    example_dict
)

Convert the given pose into a dict convertible to tf example.

from_config

@classmethod
from_config(
    root_dir: str
) -> "FeatureConnector"

Reconstructs the FeatureConnector from the config file.

Usage:

features = FeatureConnector.from_config('path/to/features.json')

Args
root_dir Directory containing to the features.json file.

Returns
The reconstructed feature instance.

from_json

@classmethod
from_json(
    value: Json
) -> "FeatureConnector"

FeatureConnector factory.

This function should be called from the tfds.features.FeatureConnector base class. Subclass should implement the from_json_content.

Example:

feature = tfds.features.FeatureConnector.from_json(
    {'type': 'Image', 'content': {'shape': [32, 32, 3], 'dtype': 'uint8'} }
)
assert isinstance(feature, tfds.features.Image)

Args
value dict(type=, content=) containing the feature to restore. Match dict returned by to_json.

Returns
The reconstructed FeatureConnector.

from_json_content

View source

@classmethod
from_json_content(
    value
) -> "Pose"

FeatureConnector factory (to overwrite).

Subclasses should overwritte this method. importing the feature connector from the config.

This function should not be called directly. FeatureConnector.from_json should be called instead.

This function See existing FeatureConnector for example of implementation.

Args
value FeatureConnector information. Match the dict returned by to_json_content.

Returns
The reconstructed FeatureConnector.

get_serialized_info

get_serialized_info()

See base class for details.

get_tensor_info

get_tensor_info()

See base class for details.

items

items()

keys

keys()

load_metadata

load_metadata(
    data_dir, feature_name=None
)

See base class for details.

repr_html

repr_html(
    ex: np.ndarray
) -> str

Returns the HTML str representation of the object.

repr_html_batch

repr_html_batch(
    ex: np.ndarray
) -> str

Returns the HTML str representation of the object (Sequence).

repr_html_ragged

repr_html_ragged(
    ex: np.ndarray
) -> str

Returns the HTML str representation of the object (Nested sequence).

save_config

save_config(
    root_dir: str
) -> None

Exports the FeatureConnector to a file.

Args
root_dir path/to/dir containing the features.json

save_metadata

save_metadata(
    data_dir, feature_name=None
)

See base class for details.

to_json

to_json() -> Json

Exports the FeatureConnector to Json.

Each feature is serialized as a dict(type=..., content=...).

  • type: The cannonical name of the feature (module.FeatureName).
  • content: is specific to each feature connector and defined in to_json_content. Can contain nested sub-features (like for tfds.features.FeaturesDict and tfds.features.Sequence).

For example:

tfds.features.FeaturesDict({
    'input': tfds.features.Image(),
    'target': tfds.features.ClassLabel(num_classes=10),
})

Is serialized as:

{
    "type": "tensorflow_datasets.core.features.features_dict.FeaturesDict",
    "content": {
        "input": {
            "type": "tensorflow_datasets.core.features.image_feature.Image",
            "content": {
                "shape": [null, null, 3],
                "dtype": "uint8",
                "encoding_format": "png"
            }
        },
        "target": {
            "type": "tensorflow_datasets.core.features.class_label_feature.ClassLabel",
            "num_classes": 10
        }
    }
}

Returns
A dict(type=, content=). Will be forwarded to from_json when reconstructing the feature.

to_json_content

View source

to_json_content()

FeatureConnector factory (to overwrite).

This function should be overwritten by the subclass to allow re-importing the feature connector from the config. See existing FeatureConnector for example of implementation.

Returns
Dict containing the FeatureConnector metadata. Will be forwarded to from_json_content when reconstructing the feature.

values

values()

__contains__

__contains__(
    k
)

__getitem__

__getitem__(
    key
)

Return the feature associated with the key.

__iter__

__iter__()

__len__

__len__()