tf.keras.losses.LogCosh
Stay organized with collections
Save and categorize content based on your preferences.
Computes the logarithm of the hyperbolic cosine of the prediction error.
Inherits From: Loss
tf.keras.losses.LogCosh(
reduction=losses_utils.ReductionV2.AUTO, name='log_cosh'
)
logcosh = log((exp(x) + exp(-x))/2),
where x is the error y_pred - y_true.
Standalone usage:
y_true = [[0., 1.], [0., 0.]]
y_pred = [[1., 1.], [0., 0.]]
# Using 'auto'/'sum_over_batch_size' reduction type.
l = tf.keras.losses.LogCosh()
l(y_true, y_pred).numpy()
0.108
# Calling with 'sample_weight'.
l(y_true, y_pred, sample_weight=[0.8, 0.2]).numpy()
0.087
# Using 'sum' reduction type.
l = tf.keras.losses.LogCosh(
reduction=tf.keras.losses.Reduction.SUM)
l(y_true, y_pred).numpy()
0.217
# Using 'none' reduction type.
l = tf.keras.losses.LogCosh(
reduction=tf.keras.losses.Reduction.NONE)
l(y_true, y_pred).numpy()
array([0.217, 0.], dtype=float32)
Usage with the compile() API:
model.compile(optimizer='sgd', loss=tf.keras.losses.LogCosh())
Args |
|---|
reduction
|
Type of tf.keras.losses.Reduction to apply to
loss. Default value is AUTO. AUTO indicates that the reduction
option will be determined by the usage context. For almost all cases
this defaults to SUM_OVER_BATCH_SIZE. When used with
tf.distribute.Strategy, outside of built-in training loops such as
tf.keras compile and fit, using AUTO or SUM_OVER_BATCH_SIZE
will raise an error. Please see this custom training tutorial for
more details.
|
name
|
Optional name for the instance. Defaults to 'log_cosh'.
|
Methods
from_config
View source
@classmethod
from_config(
config
)
Instantiates a Loss from its config (output of get_config()).
| Args |
|---|
config
|
Output of get_config().
|
get_config
View source
get_config()
Returns the config dictionary for a Loss instance.
__call__
View source
__call__(
y_true, y_pred, sample_weight=None
)
Invokes the Loss instance.
| Args |
|---|
y_true
|
Ground truth values. shape = [batch_size, d0, .. dN], except
sparse loss functions such as sparse categorical crossentropy where
shape = [batch_size, d0, .. dN-1]
|
y_pred
|
The predicted values. shape = [batch_size, d0, .. dN]
|
sample_weight
|
Optional sample_weight acts as a coefficient for the
loss. If a scalar is provided, then the loss is simply scaled by the
given value. If sample_weight is a tensor of size [batch_size], then
the total loss for each sample of the batch is rescaled by the
corresponding element in the sample_weight vector. If the shape of
sample_weight is [batch_size, d0, .. dN-1] (or can be broadcasted to
this shape), then each loss element of y_pred is scaled
by the corresponding value of sample_weight. (Note ondN-1: all loss
functions reduce by 1 dimension, usually axis=-1.)
|
| Returns |
|---|
Weighted loss float Tensor. If reduction is NONE, this has
shape [batch_size, d0, .. dN-1]; otherwise, it is scalar. (Note dN-1
because all loss functions reduce by 1 dimension, usually axis=-1.)
|
| Raises |
|---|
ValueError
|
If the shape of sample_weight is invalid.
|
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. Some content is licensed under the numpy license.
Last updated 2021-08-16 UTC.
[null,null,["Last updated 2021-08-16 UTC."],[],[],null,["# tf.keras.losses.LogCosh\n\n\u003cbr /\u003e\n\n|---------------------------------------------------------------------------------|-----------------------------------------------------------------------------------------------------|\n| [TensorFlow 1 version](/versions/r1.15/api_docs/python/tf/keras/losses/LogCosh) | [View source on GitHub](https://github.com/keras-team/keras/tree/master/keras/losses.py#L991-L1044) |\n\nComputes the logarithm of the hyperbolic cosine of the prediction error.\n\nInherits From: [`Loss`](../../../tf/keras/losses/Loss)\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.losses.LogCosh`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/LogCosh)\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.keras.losses.LogCosh`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/LogCosh)\n\n\u003cbr /\u003e\n\n tf.keras.losses.LogCosh(\n reduction=losses_utils.ReductionV2.AUTO, name='log_cosh'\n )\n\n`logcosh = log((exp(x) + exp(-x))/2)`,\nwhere x is the error `y_pred - y_true`.\n\n#### Standalone usage:\n\n y_true = [[0., 1.], [0., 0.]]\n y_pred = [[1., 1.], [0., 0.]]\n # Using 'auto'/'sum_over_batch_size' reduction type.\n l = tf.keras.losses.LogCosh()\n l(y_true, y_pred).numpy()\n 0.108\n\n # Calling with 'sample_weight'.\n l(y_true, y_pred, sample_weight=[0.8, 0.2]).numpy()\n 0.087\n\n # Using 'sum' reduction type.\n l = tf.keras.losses.LogCosh(\n reduction=tf.keras.losses.Reduction.SUM)\n l(y_true, y_pred).numpy()\n 0.217\n\n # Using 'none' reduction type.\n l = tf.keras.losses.LogCosh(\n reduction=tf.keras.losses.Reduction.NONE)\n l(y_true, y_pred).numpy()\n array([0.217, 0.], dtype=float32)\n\nUsage with the `compile()` API: \n\n model.compile(optimizer='sgd', loss=tf.keras.losses.LogCosh())\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|-------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `reduction` | Type of [`tf.keras.losses.Reduction`](../../../tf/keras/losses/Reduction) to apply to loss. Default value is `AUTO`. `AUTO` indicates that the reduction option will be determined by the usage context. For almost all cases this defaults to `SUM_OVER_BATCH_SIZE`. When used with [`tf.distribute.Strategy`](../../../tf/distribute/Strategy), outside of built-in training loops such as [`tf.keras`](../../../tf/keras) `compile` and `fit`, using `AUTO` or `SUM_OVER_BATCH_SIZE` will raise an error. Please see this custom training [tutorial](https://www.tensorflow.org/tutorials/distribute/custom_training) for more details. |\n| `name` | Optional name for the instance. Defaults to 'log_cosh'. |\n\n\u003cbr /\u003e\n\nMethods\n-------\n\n### `from_config`\n\n[View source](https://github.com/keras-team/keras/tree/master/keras/losses.py#L145-L155) \n\n @classmethod\n from_config(\n config\n )\n\nInstantiates a `Loss` from its config (output of `get_config()`).\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|----------|---------------------------|\n| `config` | Output of `get_config()`. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ||\n|---|---|\n| A `Loss` instance. ||\n\n\u003cbr /\u003e\n\n### `get_config`\n\n[View source](https://github.com/keras-team/keras/tree/master/keras/losses.py#L247-L252) \n\n get_config()\n\nReturns the config dictionary for a `Loss` instance.\n\n### `__call__`\n\n[View source](https://github.com/keras-team/keras/tree/master/keras/losses.py#L106-L143) \n\n __call__(\n y_true, y_pred, sample_weight=None\n )\n\nInvokes the `Loss` instance.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|-----------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `y_true` | Ground truth values. shape = `[batch_size, d0, .. dN]`, except sparse loss functions such as sparse categorical crossentropy where shape = `[batch_size, d0, .. dN-1]` |\n| `y_pred` | The predicted values. shape = `[batch_size, d0, .. dN]` |\n| `sample_weight` | Optional `sample_weight` acts as a coefficient for the loss. If a scalar is provided, then the loss is simply scaled by the given value. If `sample_weight` is a tensor of size `[batch_size]`, then the total loss for each sample of the batch is rescaled by the corresponding element in the `sample_weight` vector. If the shape of `sample_weight` is `[batch_size, d0, .. dN-1]` (or can be broadcasted to this shape), then each loss element of `y_pred` is scaled by the corresponding value of `sample_weight`. (Note on`dN-1`: all loss functions reduce by 1 dimension, usually axis=-1.) |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ||\n|---|---|\n| Weighted loss float `Tensor`. If `reduction` is `NONE`, this has shape `[batch_size, d0, .. dN-1]`; otherwise, it is scalar. (Note `dN-1` because all loss functions reduce by 1 dimension, usually axis=-1.) ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ||\n|--------------|---------------------------------------------|\n| `ValueError` | If the shape of `sample_weight` is invalid. |\n\n\u003cbr /\u003e"]]
TensorFlow 1 version
View source on GitHub