y_true & y_pred.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.
loss_huber(
y_true,
y_pred,
delta = 1,
...,
reduction = "sum_over_batch_size",
name = "huber_loss",
dtype = NULL
)Tensor with one scalar loss entry per sample.
tensor of true targets.
tensor of predicted targets.
A float, the point where the Huber loss function changes from a
quadratic to linear. Defaults to 1.0.
For forward/backward compatability.
Type of reduction to apply to loss. Options are "sum",
"sum_over_batch_size" or NULL. Defaults to
"sum_over_batch_size".
Optional name for the instance.
The dtype of the loss's computations. Defaults to NULL, which
means using config_floatx(). config_floatx() is a
"float32" unless set to different value
(via config_set_floatx()). If a keras$DTypePolicy is
provided, then the compute_dtype will be utilized.
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)
Other losses:
Loss()
loss_binary_crossentropy()
loss_binary_focal_crossentropy()
loss_categorical_crossentropy()
loss_categorical_focal_crossentropy()
loss_categorical_hinge()
loss_circle()
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()