Learn R Programming

keras (version 2.7.0)

metric_mean_absolute_error: Computes the mean absolute error between the labels and predictions

Description

Computes the mean absolute error between the labels and predictions

Usage

metric_mean_absolute_error(
  y_true,
  y_pred,
  ...,
  name = "mean_absolute_error",
  dtype = NULL
)

Arguments

y_true

Tensor of true targets.

y_pred

Tensor of predicted targets.

...

Passed on to the underlying metric. Used for forwards and backwards compatibility.

name

(Optional) string name of the metric instance.

dtype

(Optional) data type of the metric result.

Value

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

Alternatively, if called with y_true and y_pred arguments, then the computed case-wise values for the mini-batch are returned directly.

Details

loss = mean(abs(y_true - y_pred), axis=-1)

See Also

Other metrics: custom_metric(), metric_accuracy(), metric_auc(), metric_binary_accuracy(), metric_binary_crossentropy(), metric_categorical_accuracy(), metric_categorical_crossentropy(), metric_categorical_hinge(), metric_cosine_similarity(), metric_false_negatives(), metric_false_positives(), metric_hinge(), metric_kullback_leibler_divergence(), metric_logcosh_error(), metric_mean_absolute_percentage_error(), metric_mean_iou(), metric_mean_relative_error(), metric_mean_squared_error(), metric_mean_squared_logarithmic_error(), metric_mean_tensor(), metric_mean_wrapper(), metric_mean(), metric_poisson(), metric_precision_at_recall(), metric_precision(), metric_recall_at_precision(), metric_recall(), 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()