metric_log_cosh_error {keras3} | R Documentation |
Computes the logarithm of the hyperbolic cosine of the prediction error.
Description
Formula:
error <- y_pred - y_true logcosh <- mean(log((exp(error) + exp(-error))/2), axis=-1)
Usage
metric_log_cosh_error(..., name = "logcosh", dtype = NULL)
Arguments
... |
For forward/backward compatability. |
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.
Examples
Standalone usage:
m <- metric_log_cosh_error() m$update_state(rbind(c(0, 1), c(0, 0)), rbind(c(1, 1), c(0, 0))) m$result()
## tf.Tensor(0.108445205, shape=(), dtype=float32)
m$reset_state() m$update_state(rbind(c(0, 1), c(0, 0)), rbind(c(1, 1), c(0, 0)), sample_weight = c(1, 0)) m$result()
## tf.Tensor(0.21689041, shape=(), dtype=float32)
Usage with compile()
API:
model %>% compile(optimizer = 'sgd', loss = 'mse', metrics = list(metric_log_cosh_error()))
See Also
Other regression metrics:
metric_cosine_similarity()
metric_mean_absolute_error()
metric_mean_absolute_percentage_error()
metric_mean_squared_error()
metric_mean_squared_logarithmic_error()
metric_r2_score()
metric_root_mean_squared_error()
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_mean()
metric_mean_absolute_error()
metric_mean_absolute_percentage_error()
metric_mean_iou()
metric_mean_squared_error()
metric_mean_squared_logarithmic_error()
metric_mean_wrapper()
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()