tfr.data.build_tf_example_serving_input_receiver_fn

Builds a serving input fn for tensorflow.training.Example.

tfr.data.build_tf_example_serving_input_receiver_fn(
    context_feature_spec,
    example_feature_spec,
    size_feature_name=None,
    mask_feature_name=None,
    default_batch_size=None
)

context_feature_spec (dict) Map from feature keys to FixedLenFeature, VarLenFeature or RaggedFeature values.
example_feature_spec (dict) Map from feature keys to FixedLenFeature, VarLenFeature or RaggedFeature values.
size_feature_name (str) Name of feature for example list sizes. Populates the feature dictionary with a tf.int32 Tensor of value 1, and 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.
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.