Skip to contents

Formula:

loss <- mean(abs(y_true - y_pred))

Usage

loss_mean_absolute_error(
  y_true,
  y_pred,
  ...,
  reduction = "sum_over_batch_size",
  name = "mean_absolute_error",
  dtype = NULL
)

Arguments

y_true

Ground truth values with shape = [batch_size, d0, .. dN].

y_pred

The predicted values with shape = [batch_size, d0, .. dN].

...

For forward/backward compatability.

reduction

Type of reduction to apply to the loss. In almost all cases this should be "sum_over_batch_size". Supported options are "sum", "sum_over_batch_size" or NULL.

name

Optional name for the loss instance.

dtype

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.

Value

Mean absolute error values with shape = [batch_size, d0, .. dN-1].

Examples

y_true <- random_uniform(c(2, 3), 0, 2)
y_pred <- random_uniform(c(2, 3))
loss <- loss_mean_absolute_error(y_true, y_pred)