<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#L31-L55) |

The Glorot normal initializer, aka Xavier normal initializer.

    tfp.experimental.nn.initializers.glorot_normal(
        seed=None
    )

It draws samples from a truncated normal distribution centered on 0
with standard deviation (after truncation) given by
`stddev = sqrt(2 / (fan_in + fan_out))` where `fan_in` is the number
of input units in the weight tensor and `fan_out` is the number of
output 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 ||
|---|---|
| [Glorot et al., 2010](http://proceedings.mlr.press/v9/glorot10a.html) ([pdf](http://jmlr.org/proceedings/papers/v9/glorot10a/glorot10a.pdf)) ||

<br />