predict.tf_estimator {tfestimators} | R Documentation |
Generate Predictions with an Estimator
Description
Generate predicted labels / values for input data provided by input_fn()
.
Usage
## S3 method for class 'tf_estimator'
predict(
object,
input_fn,
checkpoint_path = NULL,
predict_keys = c("predictions", "classes", "class_ids", "logistic", "logits",
"probabilities"),
hooks = NULL,
as_iterable = FALSE,
simplify = TRUE,
yield_single_examples = TRUE,
...
)
Arguments
object |
A TensorFlow estimator. |
input_fn |
An input function, typically generated by the |
checkpoint_path |
The path to a specific model checkpoint to be used for
prediction. If |
predict_keys |
The types of predictions that should be produced, as an R list. When this argument is not specified (the default), all possible predicted values will be returned. |
hooks |
A list of R functions, to be used as callbacks inside the
training loop. By default, |
as_iterable |
Boolean; should a raw Python generator be returned? When
|
simplify |
Whether to simplify prediction results into a |
yield_single_examples |
(Available since TensorFlow v1.7) If |
... |
Optional arguments passed on to the estimator's |
Yields
Evaluated values of predictions
tensors.
Raises
ValueError: Could not find a trained model in model_dir.
ValueError: if batch length of predictions are not same. ValueError: If
there is a conflict between predict_keys
and predictions
. For example
if predict_keys
is not NULL
but EstimatorSpec.predictions
is not a
dict
.
See Also
Other custom estimator methods:
estimator_spec()
,
estimator()
,
evaluate.tf_estimator()
,
export_savedmodel.tf_estimator()
,
train.tf_estimator()