Skip to contents

Computes the categorical focal crossentropy loss.

Usage

metric_categorical_focal_crossentropy(
  y_true,
  y_pred,
  alpha = 0.25,
  gamma = 2,
  from_logits = FALSE,
  label_smoothing = 0,
  axis = -1L
)

Arguments

y_true

Tensor of one-hot true targets.

y_pred

Tensor of predicted targets.

alpha

A weight balancing factor for all classes, default is 0.25 as mentioned in the reference. It can be a list of floats or a scalar. In the multi-class case, alpha may be set by inverse class frequency by using compute_class_weight from sklearn.utils.

gamma

A focusing parameter, default is 2.0 as mentioned in the reference. It helps to gradually reduce the importance given to simple examples in a smooth manner. When gamma = 0, there is no focal effect on the categorical crossentropy.

from_logits

Whether y_pred is expected to be a logits tensor. By default, we assume that y_pred encodes a probability distribution.

label_smoothing

Float in [0, 1]. If > 0 then smooth the labels. For example, if 0.1, use 0.1 / num_classes for non-target labels and 0.9 + 0.1 / num_classes for target labels.

axis

Defaults to -1. The dimension along which the entropy is computed.

Value

Categorical focal crossentropy loss value.

Examples

y_true <- rbind(c(0, 1, 0), c(0, 0, 1))
y_pred <- rbind(c(0.05, 0.9, 0.05), c(0.1, 0.85, 0.05))
loss <- loss_categorical_focal_crossentropy(y_true, y_pred)
loss

## tf.Tensor([2.63401289e-04 6.75912094e-01], shape=(2), dtype=float64)

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_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()
metric_binary_crossentropy()
metric_binary_focal_crossentropy()
metric_categorical_crossentropy()
metric_categorical_hinge()
metric_hinge()
metric_huber()
metric_kl_divergence()
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_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_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()