|View source on GitHub|
Perform prediction using an exported saved model.
tf.contrib.timeseries.saved_model_utils.predict_continuation( continue_from, signatures, session, steps=None, times=None, exogenous_features=None )
Analogous to _input_pipeline.predict_continuation_input_fn, but operates on a saved model rather than feeding into Estimator's predict method.
continue_from: A dictionary containing the results of either an Estimator's evaluate method or filter_continuation. Used to determine the model state to make predictions starting from.
MetaGraphDefprotocol buffer returned from
tf.compat.v1.saved_model.loader.load. Used to determine the names of Tensors to feed and fetch. Must be from the same model as
session: The session to use. The session's graph must be the one into which
tf.compat.v1.saved_model.loader.loadloaded the model.
steps: The number of steps to predict (scalar), starting after the evaluation or filtering. If
stepsmust not be; one is required.
times: A [batch_size x window_size] array of integers (not a Tensor) indicating times to make predictions for. These times must be after the corresponding evaluation or filtering. If
timesmust not be; one is required. If the batch dimension is omitted, it is assumed to be 1.
exogenous_features: Optional dictionary. If specified, indicates exogenous features for the model to use while making the predictions. Values must have shape [batch_size x window_size x ...], where
batch_sizematches the batch dimension used when creating
window_sizeis either the
stepsargument or the
timesargument (depending on which was specified).
A dictionary with model-specific predictions (typically having keys "mean" and "covariance") and a feature_keys.PredictionResults.TIMES key indicating the times for which the predictions were computed.