tfp.experimental.nn.initializers.he_uniform
Stay organized with collections
Save and categorize content based on your preferences.
He uniform variance scaling initializer.
tfp.experimental.nn.initializers.he_uniform(
seed=None
)
It draws samples from a uniform distribution within [-limit, limit]
where limit is sqrt(6 / fan_in)
where fan_in is the number of input units in the weight tensor.
Returns |
|---|
init_fn
|
A python callable which takes a shape Tensor, dtype and an
optional scalar int number of batch dims and returns a randomly
initialized Tensor with the specified shape and dtype.
|
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 2023-11-21 UTC.
[null,null,["Last updated 2023-11-21 UTC."],[],[],null,["# tfp.experimental.nn.initializers.he_uniform\n\n\u003cbr /\u003e\n\n|----------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/probability/blob/v0.23.0/tensorflow_probability/python/experimental/nn/initializers/initializers.py#L112-L137) |\n\nHe uniform variance scaling initializer. \n\n tfp.experimental.nn.initializers.he_uniform(\n seed=None\n )\n\nIt draws samples from a uniform distribution within \\[-limit, limit\\]\nwhere `limit` is `sqrt(6 / fan_in)`\nwhere `fan_in` is the number of input units in the weight tensor.\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|--------|-----------------------------------------------------------------------------------------------------------------------|\n| `seed` | PRNG seed; see [`tfp.random.sanitize_seed`](../../../../tfp/random/sanitize_seed) for details. Default value: `None`. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|-----------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| `init_fn` | A python `callable` which takes a shape `Tensor`, dtype and an optional scalar `int` number of batch dims and returns a randomly initialized `Tensor` with the specified shape and dtype. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| References ---------- ||\n|---|---|\n| [He et al., 2015](https://www.cv-foundation.org/openaccess/content_iccv_2015/html/He_Delving_Deep_into_ICCV_2015_paper.html) ([pdf](https://www.cv-foundation.org/openaccess/content_iccv_2015/papers/He_Delving_Deep_into_ICCV_2015_paper.pdf)) ||\n\n\u003cbr /\u003e"]]
View source on GitHub