Google I/O is a wrap! Catch up on TensorFlow sessions View sessions

tfr.keras.model.FeatureSpecInputCreator

InputCreator with feature specs.

Inherits From: InputCreator

tfr.keras.model.FeatureSpecInputCreator(
    context_feature_spec: Dict[str, Union[tf.io.FixedLenFeature, tf.io.VarLenFeature, tf.io.
        RaggedFeature]],
    example_feature_spec: Dict[str, Union[tf.io.FixedLenFeature, tf.io.VarLenFeature, tf.io.
        RaggedFeature]]
)

Example usage:

input_creator=FeatureSpecInputCreator(
    {},
    {"example_feature_1": tf.io.FixedLenFeature(
        shape=(1,), dtype=tf.float32, default_value=0.0)})

context_feature_spec A dict maps the context feature keys to the corresponding context feature specs.
example_feature_spec A dict maps the example feature keys to the corresponding example feature specs.

Methods

__call__

View source

__call__() -> Tuple[tfr.keras.model.TensorDict, tfr.keras.model.TensorDict]

See InputCreator.