tfr.data.build_ranking_serving_input_receiver_fn

Returns a serving input receiver fn for a standard data format.

tfr.data.build_ranking_serving_input_receiver_fn(
    data_format,
    context_feature_spec,
    example_feature_spec,
    list_size=None,
    size_feature_name=None,
    mask_feature_name=None,
    receiver_name='input_ranking_data',
    default_batch_size=None
)

data_format (string) See RankingDataFormat.
context_feature_spec (dict) Map from feature keys to FixedLenFeature or VarLenFeature values.
example_feature_spec (dict) Map from feature keys to FixedLenFeature or VarLenFeature values.
list_size (int) The number of examples to keep. If specified, truncation or padding may happen. Otherwise, set it to None to allow dynamic list size (recommended).
size_feature_name (str) Name of feature for example list sizes. Populates the feature dictionary with a tf.int32 Tensor of shape [batch_size] for this feature name. If None, which is default, this feature is not generated.
mask_feature_name (str) Name of feature for example list masks. Populates the feature dictionary with a tf.bool Tensor of shape [batch_size, list_size] for this feature name. If None, which is default, this feature is not generated.
receiver_name (string) The name for the receiver tensor.
default_batch_size (int) Number of instances expected per batch. Leave unset for variable batch size (recommended).

A tf.estimator.export.ServingInputReceiver object, which packages the placeholders and the resulting feature Tensors together.