Evaluate an Estimator
Evaluate an estimator on input data provided by an
# S3 method for tf_estimator evaluate(object, input_fn, steps = NULL, checkpoint_path = NULL, name = NULL, hooks = NULL, simplify = TRUE, ...)
A TensorFlow estimator.
An input function, typically generated by the
The number of steps for which the model should be evaluated on
The path to a specific model checkpoint to be used for
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.
A list of R functions, to be used as callbacks inside the
training loop. By default,
Whether to simplify evaluation results into a
Optional arguments passed on to the estimator's
An R list of evaluation metrics.
For each step, this method will call
input_fn() to produce a single batch
of data. Evaluation continues until:
stepsbatches are processed, or
input_fn()is exhausted of data.