tf.losses.get_total_loss
Stay organized with collections
Save and categorize content based on your preferences.
Returns a tensor whose value represents the total loss.
tf.losses.get_total_loss(
add_regularization_losses=True, name='total_loss', scope=None
)
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.
|
scope
|
An optional scope name for filtering the losses to return. Note that
this filters the losses added with tf.add_loss() as well as the
regularization losses to that scope.
|
Returns |
|---|
A Tensor whose value represents the total loss.
|
Raises |
|---|
ValueError
|
if losses is not iterable.
|
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2020-10-01 UTC.
[null,null,["Last updated 2020-10-01 UTC."],[],[],null,["# tf.losses.get_total_loss\n\n\u003cbr /\u003e\n\n|-------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/losses/util.py#L242-L271) |\n\nReturns a tensor whose value represents the total loss.\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.losses.get_total_loss`](/api_docs/python/tf/compat/v1/losses/get_total_loss)\n\n\u003cbr /\u003e\n\n tf.losses.get_total_loss(\n add_regularization_losses=True, name='total_loss', scope=None\n )\n\nIn particular, this adds any losses you have added with `tf.add_loss()` to\nany regularization losses that have been added by regularization parameters\non layers constructors e.g. [`tf.layers`](../../tf/layers). Be very sure to use this if you\nare constructing a loss_op manually. Otherwise regularization arguments\non [`tf.layers`](../../tf/layers) methods will not function.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-----------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `add_regularization_losses` | A boolean indicating whether or not to use the regularization losses in the sum. |\n| `name` | The name of the returned tensor. |\n| `scope` | An optional scope name for filtering the losses to return. Note that this filters the losses added with `tf.add_loss()` as well as the regularization losses to that scope. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A `Tensor` whose value represents the total loss. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|--------------|------------------------------|\n| `ValueError` | if `losses` is not iterable. |\n\n\u003cbr /\u003e"]]
View source on GitHub