tf.losses.absolute_difference

tf.losses.absolute_difference

tf.losses.absolute_difference

absolute_difference(
    labels,
    predictions,
    weights=1.0,
    scope=None,
    loss_collection=tf.GraphKeys.LOSSES,
    reduction=Reduction.SUM_BY_NONZERO_WEIGHTS
)

Defined in tensorflow/python/ops/losses/losses_impl.py.

Adds an Absolute Difference loss to the training procedure.

weights acts as a coefficient for the loss. If a scalar is provided, then the loss is simply