evaluate.tf_estimator {tfestimators} | R Documentation |
Evaluate an Estimator
Description
Evaluate an estimator on input data provided by an input_fn()
.
Usage
## S3 method for class 'tf_estimator'
evaluate(
object,
input_fn,
steps = NULL,
checkpoint_path = NULL,
name = NULL,
hooks = NULL,
simplify = TRUE,
...
)
Arguments
object |
A TensorFlow estimator. |
input_fn |
An input function, typically generated by the |
steps |
The number of steps for which the model should be evaluated on
this particular |
checkpoint_path |
The path to a specific model checkpoint to be used for
prediction. If |
name |
Name of the evaluation if user needs to run multiple evaluations on different data sets, such as on training data vs test data. Metrics for different evaluations are saved in separate folders, and appear separately in tensorboard. |
hooks |
A list of R functions, to be used as callbacks inside the
training loop. By default, |
simplify |
Whether to simplify evaluation results into a |
... |
Optional arguments passed on to the estimator's |
Details
For each step, this method will call input_fn()
to produce a single batch
of data. Evaluation continues until:
-
steps
batches are processed, or The
input_fn()
is exhausted of data.
Value
An R list of evaluation metrics.
See Also
Other custom estimator methods:
estimator_spec()
,
estimator()
,
export_savedmodel.tf_estimator()
,
predict.tf_estimator()
,
train.tf_estimator()