View source on GitHub |
Computes the mean absolute percentage error between y_true
& y_pred
.
Inherits From: Loss
tf.keras.losses.MeanAbsolutePercentageError(
reduction='sum_over_batch_size',
name='mean_absolute_percentage_error'
)
Formula:
loss = 100 * mean(abs((y_true - y_pred) / y_true))
Methods
call
call(
y_true, y_pred
)
from_config
@classmethod
from_config( config )
get_config
get_config()
__call__
__call__(
y_true, y_pred, sample_weight=None
)
Call self as a function.