Type tf.estimator.export
Namespace tensorflow
Methods
Properties
Public static methods
object build_parsing_serving_input_receiver_fn(IDictionary<object, FixedLenFeature> feature_spec, object default_batch_size)
Build a serving_input_receiver_fn expecting fed tf.Examples. Creates a serving_input_receiver_fn that expects a serialized tf.Example fed
into a string placeholder. The function parses the tf.Example according to
the provided feature_spec, and returns all parsed Tensors as features.
Parameters
-
IDictionary<object, FixedLenFeature>feature_spec - a dict of string to `VarLenFeature`/`FixedLenFeature`.
-
objectdefault_batch_size - the number of query examples expected per batch. Leave unset for variable batch size (recommended).
Returns
-
object - A serving_input_receiver_fn suitable for use in serving.
object build_parsing_serving_input_receiver_fn_dyn(object feature_spec, object default_batch_size)
Build a serving_input_receiver_fn expecting fed tf.Examples. Creates a serving_input_receiver_fn that expects a serialized tf.Example fed
into a string placeholder. The function parses the tf.Example according to
the provided feature_spec, and returns all parsed Tensors as features.
Parameters
-
objectfeature_spec - a dict of string to `VarLenFeature`/`FixedLenFeature`.
-
objectdefault_batch_size - the number of query examples expected per batch. Leave unset for variable batch size (recommended).
Returns
-
object - A serving_input_receiver_fn suitable for use in serving.