tf.keras.initializers.VarianceScaling
Stay organized with collections
Save and categorize content based on your preferences.
Initializer that adapts its scale to the shape of its input tensors.
Inherits From: Initializer
tf.keras.initializers.VarianceScaling(
scale=1.0,
mode='fan_in',
distribution='truncated_normal',
seed=None
)
Used in the notebooks
With distribution="truncated_normal" or "untruncated_normal", samples are
drawn from a truncated/untruncated normal distribution with a mean of zero
and a standard deviation (after truncation, if used) stddev = sqrt(scale /
n), where n is:
- number of input units in the weight tensor, if
mode="fan_in"
- number of output units, if
mode="fan_out"
- average of the numbers of input and output units, if
mode="fan_avg"
With distribution="uniform", samples are drawn from a uniform distribution
within [-limit, limit], where limit = sqrt(3 * scale / n).
Examples:
# Standalone usage:
initializer = VarianceScaling(
scale=0.1, mode='fan_in', distribution='uniform')
values = initializer(shape=(2, 2))
# Usage in a Keras layer:
initializer = VarianceScaling(
scale=0.1, mode='fan_in', distribution='uniform')
layer = Dense(3, kernel_initializer=initializer)
Args |
|---|
scale
|
Scaling factor (positive float).
|
mode
|
One of "fan_in", "fan_out", "fan_avg".
|
distribution
|
Random distribution to use.
One of "truncated_normal", "untruncated_normal", or "uniform".
|
seed
|
A Python integer or instance of
keras.backend.SeedGenerator.
Used to make the behavior of the initializer
deterministic. Note that an initializer seeded with an integer
or None (unseeded) will produce the same random values
across multiple calls. To get different random values
across multiple calls, use as seed an instance
of keras.backend.SeedGenerator.
|
Methods
clone
View source
clone()
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
)
Returns a tensor object initialized as specified by the initializer.
| Args |
|---|
shape
|
Shape of the tensor.
|
dtype
|
Optional dtype of the tensor.
|
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 2024-06-07 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 2024-06-07 UTC."],[],[],null,["# tf.keras.initializers.VarianceScaling\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/keras-team/keras/tree/v3.3.3/keras/src/initializers/random_initializers.py#L188-L305) |\n\nInitializer that adapts its scale to the shape of its input tensors.\n\nInherits From: [`Initializer`](../../../tf/keras/Initializer)\n\n#### View aliases\n\n\n**Main aliases**\n\n[`tf.keras.initializers.variance_scaling`](https://www.tensorflow.org/api_docs/python/tf/keras/initializers/VarianceScaling)\n\n\u003cbr /\u003e\n\n tf.keras.initializers.VarianceScaling(\n scale=1.0,\n mode='fan_in',\n distribution='truncated_normal',\n seed=None\n )\n\n### Used in the notebooks\n\n| Used in the tutorials |\n|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| - [Train a Deep Q Network with TF-Agents](https://www.tensorflow.org/agents/tutorials/1_dqn_tutorial) - [Networks](https://www.tensorflow.org/agents/tutorials/8_networks_tutorial) |\n\nWith `distribution=\"truncated_normal\" or \"untruncated_normal\"`, samples are\ndrawn from a truncated/untruncated normal distribution with a mean of zero\nand a standard deviation (after truncation, if used) `stddev = sqrt(scale /\nn)`, where `n` is:\n\n- number of input units in the weight tensor, if `mode=\"fan_in\"`\n- number of output units, if `mode=\"fan_out\"`\n- average of the numbers of input and output units, if `mode=\"fan_avg\"`\n\nWith `distribution=\"uniform\"`, samples are drawn from a uniform distribution\nwithin `[-limit, limit]`, where `limit = sqrt(3 * scale / n)`.\n\n#### Examples:\n\n # Standalone usage:\n initializer = VarianceScaling(\n scale=0.1, mode='fan_in', distribution='uniform')\n values = initializer(shape=(2, 2))\n\n # Usage in a Keras layer:\n initializer = VarianceScaling(\n scale=0.1, mode='fan_in', distribution='uniform')\n layer = Dense(3, kernel_initializer=initializer)\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|----------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `scale` | Scaling factor (positive float). |\n| `mode` | One of `\"fan_in\"`, `\"fan_out\"`, `\"fan_avg\"`. |\n| `distribution` | Random distribution to use. One of `\"truncated_normal\"`, `\"untruncated_normal\"`, or `\"uniform\"`. |\n| `seed` | A Python integer or instance of `keras.backend.SeedGenerator`. Used to make the behavior of the initializer deterministic. Note that an initializer seeded with an integer or `None` (unseeded) will produce the same random values across multiple calls. To get different random values across multiple calls, use as seed an instance of `keras.backend.SeedGenerator`. |\n\n\u003cbr /\u003e\n\nMethods\n-------\n\n### `clone`\n\n[View source](https://github.com/keras-team/keras/tree/v3.3.3/keras/src/initializers/initializer.py#L83-L84) \n\n clone()\n\n### `from_config`\n\n[View source](https://github.com/keras-team/keras/tree/v3.3.3/keras/src/initializers/initializer.py#L63-L81) \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/v3.3.3/keras/src/initializers/random_initializers.py#L298-L305) \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/v3.3.3/keras/src/initializers/random_initializers.py#L273-L296) \n\n __call__(\n shape, dtype=None\n )\n\nReturns a tensor object initialized as specified by the initializer.\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. |\n\n\u003cbr /\u003e"]]
View source on GitHub