<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/experimental/nn/initializers/initializers.py#L112-L137) |

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.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `seed` | PRNG seed; see [`tfp.random.sanitize_seed`](https://www.tensorflow.org/probability/api_docs/python/tfp/random/sanitize_seed) for details. Default value: `None`. |

<br />

<br />

<br />

<br />

| ## 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. |

<br />

<br />

<br />

<br />

| ## References ||
|---|---|
| [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)) ||

<br />