tf.keras.losses.MeanSquaredLogarithmicError
Stay organized with collections
Save and categorize content based on your preferences.
Computes the mean squared logarithmic error between y_true & y_pred.
Inherits From: Loss
tf.keras.losses.MeanSquaredLogarithmicError(
reduction=losses_utils.ReductionV2.AUTO,
name='mean_squared_logarithmic_error'
)
loss = square(log(y_true + 1.) - log(y_pred + 1.))
Standalone usage:
y_true = [[0., 1.], [0., 0.]]
y_pred = [[1., 1.], [1., 0.]]
# Using 'auto'/'sum_over_batch_size' reduction type.
msle = tf.keras.losses.MeanSquaredLogarithmicError()
msle(y_true, y_pred).numpy()
0.240
# Calling with 'sample_weight'.
msle(y_true, y_pred, sample_weight=[0.7, 0.3]).numpy()
0.120
# Using 'sum' reduction type.
msle = tf.keras.losses.MeanSquaredLogarithmicError(
reduction=tf.keras.losses.Reduction.SUM)
msle(y_true, y_pred).numpy()
0.480
# Using 'none' reduction type.
msle = tf.keras.losses.MeanSquaredLogarithmicError(
reduction=tf.keras.losses.Reduction.NONE)
msle(y_true, y_pred).numpy()
array([0.240, 0.240], dtype=float32)
Usage with the compile() API:
model.compile(optimizer='sgd',
loss=tf.keras.losses.MeanSquaredLogarithmicError())
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 under a tf.distribute.Strategy, except via
Model.compile() and Model.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
'mean_squared_logarithmic_error'.
|
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 2023-10-06 UTC.
[null,null,["Last updated 2023-10-06 UTC."],[],[],null,["# tf.keras.losses.MeanSquaredLogarithmicError\n\n\u003cbr /\u003e\n\n|-----------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v2.14.0/keras/losses.py#L496-L558) |\n\nComputes the mean squared logarithmic error between `y_true` \\& `y_pred`.\n\nInherits From: [`Loss`](../../../tf/keras/losses/Loss)\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.losses.MeanSquaredLogarithmicError`](https://www.tensorflow.org/api_docs/python/tf/keras/losses/MeanSquaredLogarithmicError)\n\n\u003cbr /\u003e\n\n tf.keras.losses.MeanSquaredLogarithmicError(\n reduction=losses_utils.ReductionV2.AUTO,\n name='mean_squared_logarithmic_error'\n )\n\n`loss = square(log(y_true + 1.) - log(y_pred + 1.))`\n\n#### Standalone usage:\n\n y_true = [[0., 1.], [0., 0.]]\n y_pred = [[1., 1.], [1., 0.]]\n # Using 'auto'/'sum_over_batch_size' reduction type.\n msle = tf.keras.losses.MeanSquaredLogarithmicError()\n msle(y_true, y_pred).numpy()\n 0.240\n\n # Calling with 'sample_weight'.\n msle(y_true, y_pred, sample_weight=[0.7, 0.3]).numpy()\n 0.120\n\n # Using 'sum' reduction type.\n msle = tf.keras.losses.MeanSquaredLogarithmicError(\n reduction=tf.keras.losses.Reduction.SUM)\n msle(y_true, y_pred).numpy()\n 0.480\n\n # Using 'none' reduction type.\n msle = tf.keras.losses.MeanSquaredLogarithmicError(\n reduction=tf.keras.losses.Reduction.NONE)\n msle(y_true, y_pred).numpy()\n array([0.240, 0.240], dtype=float32)\n\nUsage with the `compile()` API: \n\n model.compile(optimizer='sgd',\n loss=tf.keras.losses.MeanSquaredLogarithmicError())\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 under a [`tf.distribute.Strategy`](../../../tf/distribute/Strategy), except via [`Model.compile()`](../../../tf/keras/Model#compile) and [`Model.fit()`](../../../tf/keras/Model#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 'mean_squared_logarithmic_error'. |\n\n\u003cbr /\u003e\n\nMethods\n-------\n\n### `from_config`\n\n[View source](https://github.com/keras-team/keras/tree/v2.14.0/keras/losses.py#L287-L301) \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 [`keras.losses.Loss`](../../../tf/keras/losses/Loss) instance. ||\n\n\u003cbr /\u003e\n\n### `get_config`\n\n[View source](https://github.com/keras-team/keras/tree/v2.14.0/keras/losses.py#L272-L285) \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/v2.14.0/keras/losses.py#L102-L163) \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"]]
View source on GitHub