tf.keras.initializers.Orthogonal
Stay organized with collections
Save and categorize content based on your preferences.
Initializer that generates an orthogonal matrix.
Inherits From: Initializer
tf.keras.initializers.Orthogonal(
gain=1.0, seed=None
)
Also available via the shortcut function tf.keras.initializers.orthogonal.
If the shape of the tensor to initialize is two-dimensional, it is
initialized with an orthogonal matrix obtained from the QR decomposition of
a matrix of random numbers drawn from a normal distribution. If the matrix
has fewer rows than columns then the output will have orthogonal rows.
Otherwise, the output will have orthogonal columns.
If the shape of the tensor to initialize is more than two-dimensional,
a matrix of shape (shape[0] * ... * shape[n - 2], shape[n - 1])
is initialized, where n is the length of the shape vector.
The matrix is subsequently reshaped to give a tensor of the desired shape.
Examples:
# Standalone usage:
initializer = tf.keras.initializers.Orthogonal()
values = initializer(shape=(2, 2))
# Usage in a Keras layer:
initializer = tf.keras.initializers.Orthogonal()
layer = tf.keras.layers.Dense(3, kernel_initializer=initializer)
Args |
|---|
gain
|
multiplicative factor to apply to the orthogonal matrix
|
seed
|
A Python integer. Used to make the behavior of the initializer
deterministic. Note that a seeded initializer will produce the same
random values across multiple calls.
|
Methods
from_config
View source
@classmethod
from_config(
config
)
Instantiates an initializer from a configuration dictionary.
Example:
initializer = RandomUniform(-1, 1)
config = initializer.get_config()
initializer = RandomUniform.from_config(config)
| Args |
|---|
config
|
A Python dictionary, the output of get_config().
|
| Returns |
|---|
An Initializer instance.
|
get_config
View source
get_config()
Returns the initializer's configuration as a JSON-serializable dict.
| Returns |
|---|
|
A JSON-serializable Python dict.
|
__call__
View source
__call__(
shape, dtype=None, **kwargs
)
Returns a tensor object initialized to an orthogonal matrix.
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.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2023-10-06 UTC."],[],[],null,["# tf.keras.initializers.Orthogonal\n\n\u003cbr /\u003e\n\n|------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v2.13.1/keras/initializers/initializers.py#L685-L783) |\n\nInitializer that generates an orthogonal matrix.\n\nInherits From: [`Initializer`](../../../tf/keras/initializers/Initializer)\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.initializers.Orthogonal`](https://www.tensorflow.org/api_docs/python/tf/keras/initializers/Orthogonal), [`tf.initializers.orthogonal`](https://www.tensorflow.org/api_docs/python/tf/keras/initializers/Orthogonal), [`tf.keras.initializers.orthogonal`](https://www.tensorflow.org/api_docs/python/tf/keras/initializers/Orthogonal)\n\n\u003cbr /\u003e\n\n tf.keras.initializers.Orthogonal(\n gain=1.0, seed=None\n )\n\nAlso available via the shortcut function [`tf.keras.initializers.orthogonal`](../../../tf/keras/initializers/Orthogonal).\n\nIf the shape of the tensor to initialize is two-dimensional, it is\ninitialized with an orthogonal matrix obtained from the QR decomposition of\na matrix of random numbers drawn from a normal distribution. If the matrix\nhas fewer rows than columns then the output will have orthogonal rows.\nOtherwise, the output will have orthogonal columns.\n\nIf the shape of the tensor to initialize is more than two-dimensional,\na matrix of shape `(shape[0] * ... * shape[n - 2], shape[n - 1])`\nis initialized, where `n` is the length of the shape vector.\nThe matrix is subsequently reshaped to give a tensor of the desired shape.\n\n#### Examples:\n\n # Standalone usage:\n initializer = tf.keras.initializers.Orthogonal()\n values = initializer(shape=(2, 2))\n\n # Usage in a Keras layer:\n initializer = tf.keras.initializers.Orthogonal()\n layer = tf.keras.layers.Dense(3, kernel_initializer=initializer)\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|--------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `gain` | multiplicative factor to apply to the orthogonal matrix |\n| `seed` | A Python integer. Used to make the behavior of the initializer deterministic. Note that a seeded initializer will produce the same random values across multiple calls. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| References ---------- ||\n|---|---|\n| \u003cbr /\u003e - [Saxe et al., 2014](https://openreview.net/forum?id=_wzZwKpTDF_9C) ||\n\n\u003cbr /\u003e\n\nMethods\n-------\n\n### `from_config`\n\n[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/initializers/initializers.py#L96-L115) \n\n @classmethod\n from_config(\n config\n )\n\nInstantiates an initializer from a configuration dictionary.\n\n#### Example:\n\n initializer = RandomUniform(-1, 1)\n config = initializer.get_config()\n initializer = RandomUniform.from_config(config)\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|----------|----------------------------------------------------|\n| `config` | A Python dictionary, the 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| An `Initializer` instance. ||\n\n\u003cbr /\u003e\n\n### `get_config`\n\n[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/initializers/initializers.py#L782-L783) \n\n get_config()\n\nReturns the initializer's configuration as a JSON-serializable dict.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ||\n|---|---|\n| A JSON-serializable Python dict. ||\n\n\u003cbr /\u003e\n\n### `__call__`\n\n[View source](https://github.com/keras-team/keras/tree/v2.13.1/keras/initializers/initializers.py#L731-L760) \n\n __call__(\n shape, dtype=None, **kwargs\n )\n\nReturns a tensor object initialized to an orthogonal matrix.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ||\n|------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `shape` | Shape of the tensor. |\n| `dtype` | Optional dtype of the tensor. Only floating point types are supported. If not specified, [`tf.keras.backend.floatx()`](../../../tf/keras/backend/floatx) is used, which default to `float32` unless you configured it otherwise (via [`tf.keras.backend.set_floatx(float_dtype)`](../../../tf/keras/backend/set_floatx)) |\n| `**kwargs` | Additional keyword arguments. |\n\n\u003cbr /\u003e"]]
View source on GitHub