tf.nn.compute_average_loss

Scales per-example losses with sample_weights and computes their average.

tf.nn.compute_average_loss(
    per_example_loss, sample_weight=None, global_batch_size=None
)

Usage with distribution strategy and custom training loop:

with strategy.scope():
  def compute_loss(labels, predictions, sample_weight=None):

    # If you are using a `Loss` class instead, set reduction to `NONE` so that
    # we can do the reduction afterwards and divide by global batch size.
    per_example_loss = tf.keras.losses.sparse_categorical_crossentropy(
        labels, predictions)

    # Compute loss that is scaled by sample_weight and by global batch size.
    return tf.nn.compute_average_loss(
        per_example_loss,
        sample_weight=sample_weight,
        global_batch_size=GLOBAL_BATCH_SIZE)

per_example_loss Per-example loss.
sample_weight Optional weighting for each example.
global_batch_size Optional global batch size value. Defaults to (size of first dimension of losses) * (number of replicas).

Scalar loss value, obtained by summing the per_example_loss and dividing by global_batch_size. If global_batch_size is zero, the result is zero.