tf.losses.get_total_loss( add_regularization_losses=True, name='total_loss' )
Returns a tensor whose value represents the total loss.
In particular, this adds any losses you have added with
any regularization losses that have been added by regularization parameters
on layers constructors e.g.
tf.layers. Be very sure to use this if you
are constructing a loss_op manually. Otherwise regularization arguments
tf.layers methods will not function.
add_regularization_losses: A boolean indicating whether or not to use the regularization losses in the sum.
name: The name of the returned tensor.
Tensor whose value represents the total loss.
lossesis not iterable.