Skip to contents

Formula:

loss <- y_true * log(y_true / y_pred)

y_true and y_pred are expected to be probability distributions, with values between 0 and 1. They will get clipped to the [0, 1] range.

Usage

metric_kl_divergence(y_true, y_pred, ..., name = "kl_divergence", dtype = NULL)

Arguments

y_true

Tensor of true targets.

y_pred

Tensor of predicted targets.

...

For forward/backward compatability.

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 Metric instance is returned. The Metric instance that can be passed directly to compile(metrics = ), or used as a standalone object. See ?Metric for example usage. If y_true and y_pred are provided, then a tensor with the computed value is returned.

Usage

Standalone usage:

m <- metric_kl_divergence()
m$update_state(rbind(c(0, 1), c(0, 0)), rbind(c(0.6, 0.4), c(0.4, 0.6)))
m$result()

## tf.Tensor(0.45814303, shape=(), dtype=float32)

m$reset_state()
m$update_state(rbind(c(0, 1), c(0, 0)), rbind(c(0.6, 0.4), c(0.4, 0.6)),
               sample_weight = c(1, 0))
m$result()

## tf.Tensor(0.91628915, shape=(), dtype=float32)

Usage with compile() API:

model %>% compile(optimizer = 'sgd',
                  loss = 'mse',
                  metrics = list(metric_kl_divergence()))

See also

Other losses:
Loss()
loss_binary_crossentropy()
loss_binary_focal_crossentropy()
loss_categorical_crossentropy()
loss_categorical_focal_crossentropy()
loss_categorical_hinge()
loss_cosine_similarity()
loss_ctc()
loss_dice()
loss_hinge()
loss_huber()
loss_kl_divergence()
loss_log_cosh()
loss_mean_absolute_error()
loss_mean_absolute_percentage_error()
loss_mean_squared_error()
loss_mean_squared_logarithmic_error()
loss_poisson()
loss_sparse_categorical_crossentropy()
loss_squared_hinge()
loss_tversky()
metric_binary_crossentropy()
metric_binary_focal_crossentropy()
metric_categorical_crossentropy()
metric_categorical_focal_crossentropy()
metric_categorical_hinge()
metric_hinge()
metric_huber()
metric_log_cosh()
metric_mean_absolute_error()
metric_mean_absolute_percentage_error()
metric_mean_squared_error()
metric_mean_squared_logarithmic_error()
metric_poisson()
metric_sparse_categorical_crossentropy()
metric_squared_hinge()

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_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_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()

Other probabilistic metrics:
metric_binary_crossentropy()
metric_categorical_crossentropy()
metric_poisson()
metric_sparse_categorical_crossentropy()