tf.nn.collapse

TensorFlow 1 version

View source on GitHub

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

View aliases

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.nn.compute_average_loss

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

Used in the notebooks

Used in the guide	Used in the tutorials
Use TPUs Distributed training with TensorFlow	Custom training with tf.distribute.Strategy Parameter Server Training

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)

Args
`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).

Returns
Scalar loss value.

TensorFlow

tf

tf.audio

tf.autograph

tf.bitwise

tf.compat

tf.config

tf.data

tf.debugging

tf.distribute

tf.dtypes

tf.errors

tf.estimator

tf.experimental

tf.feature_column

tf.graph_util

tf.image

tf.initializers

tf.io

tf.keras

tf.linalg

tf.lite

tf.lookup

tf.losses

tf.math

tf.metrics

tf.nest

tf.nn

tf.optimizers

tf.quantization

tf.queue

tf.ragged

tf.random

tf.raw_ops

tf.saved_model

tf.sets

tf.signal

tf.sparse

tf.strings

tf.summary

tf.sysconfig

tf.test

tf.tpu

tf.train

tf.version

tf.xla

tf.nn / collapse_repeated

View aliases

Used in the notebooks

Args

Returns