metric_mean_wrapper {keras3}

Wrap a stateless metric function with the Mean metric.

Description

You could use this class to quickly build a mean metric from a function. The function needs to have the signature fn(y_true, y_pred) and return a per-sample loss array. metric_mean_wrapper$result() will return the average metric value across all samples seen so far.

For example:

mse <- function(y_true, y_pred) {
  (y_true - y_pred)^2
}

mse_metric <- metric_mean_wrapper(fn = mse)
mse_metric$update_state(c(0, 1), c(1, 1))
mse_metric$result()

## tf.Tensor(0.5, shape=(), dtype=float32)

Usage

metric_mean_wrapper(..., fn, name = NULL, dtype = NULL)

Arguments

...

Keyword arguments to pass on to fn.

fn

The metric function to wrap, with signature fn(y_true, y_pred).

name

(Optional) string name of the metric instance.

dtype

(Optional) data type of the metric result.

Value

a Metric instance is returned. The Metric instance can be passed directly to compile(metrics = ), or used as a standalone object. See ?Metric for example usage.

See Also

Other reduction metrics:
metric_mean()
metric_sum()

Other metrics:
Metric()
custom_metric()
metric_auc()
metric_binary_accuracy()
metric_binary_crossentropy()
metric_binary_focal_crossentropy()
metric_binary_iou()
metric_categorical_accuracy()
metric_categorical_crossentropy()
metric_categorical_focal_crossentropy()
metric_categorical_hinge()
metric_cosine_similarity()
metric_f1_score()
metric_false_negatives()
metric_false_positives()
metric_fbeta_score()
metric_hinge()
metric_huber()
metric_iou()
metric_kl_divergence()
metric_log_cosh()
metric_log_cosh_error()
metric_mean()
metric_mean_absolute_error()
metric_mean_absolute_percentage_error()
metric_mean_iou()
metric_mean_squared_error()
metric_mean_squared_logarithmic_error()
metric_one_hot_iou()
metric_one_hot_mean_iou()
metric_poisson()
metric_precision()
metric_precision_at_recall()
metric_r2_score()
metric_recall()
metric_recall_at_precision()
metric_root_mean_squared_error()
metric_sensitivity_at_specificity()
metric_sparse_categorical_accuracy()
metric_sparse_categorical_crossentropy()
metric_sparse_top_k_categorical_accuracy()
metric_specificity_at_sensitivity()
metric_squared_hinge()
metric_sum()
metric_top_k_categorical_accuracy()
metric_true_negatives()
metric_true_positives()