Computes the Huber loss between y_true & y_pred. — loss_huber • keras3

Formula:

for (x in error) {
  if (abs(x) <= delta){
    loss <- c(loss, (0.5 * x^2))
  } else if (abs(x) > delta) {
    loss <- c(loss, (delta * abs(x) - 0.5 * delta^2))
  }
}
loss <- mean(loss)

See: Huber loss.

Usage

loss_huber(
  y_true,
  y_pred,
  delta = 1,
  ...,
  reduction = "sum_over_batch_size",
  name = "huber_loss"
)

Arguments

y_true: tensor of true targets.
y_pred: tensor of predicted targets.
delta: A float, the point where the Huber loss function changes from a quadratic to linear. Defaults to 1.0.
...: For forward/backward compatability.
reduction: Type of reduction to apply to loss. Options are "sum", "sum_over_batch_size" or NULL. Defaults to "sum_over_batch_size".
name: Optional name for the instance.

Value

Tensor with one scalar loss entry per sample.

Examples

y_true <- rbind(c(0, 1), c(0, 0))
y_pred <- rbind(c(0.6, 0.4), c(0.4, 0.6))
loss <- loss_huber(y_true, y_pred)

See also

https://keras.io/api/losses/regression_losses#huber-class

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_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_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()