Watch talks from the 2019 TensorFlow Dev Summit Watch now

tf.losses.get_total_loss

tf.losses.get_total_loss(
    add_regularization_losses=True,
    name='total_loss'
)

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

Returns a tensor whose value represents the total loss.

In particular, this adds any losses you have added with tf.add_loss() to 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 on tf.layers methods will not function.

Args:

  • add_regularization_losses: A boolean indicating whether or not to use the regularization losses in the sum.
  • name: The name of the returned tensor.

Returns:

A Tensor whose value represents the total loss.

Raises:

  • ValueError: if losses is not iterable.