# tf.keras.initializers.HeNormal

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.3.0/tensorflow/python/keras/initializers/initializers_v2.py#L670-L704) |

He normal initializer.

Inherits From: [`VarianceScaling`](https://www.tensorflow.org/versions/r2.3/api_docs/python/tf/keras/initializers/VarianceScaling)

#### View aliases


**Main aliases**

[`tf.initializers.HeNormal`](https://www.tensorflow.org/api_docs/python/tf/keras/initializers/HeNormal), [`tf.initializers.he_normal`](https://www.tensorflow.org/api_docs/python/tf/keras/initializers/HeNormal), [`tf.keras.initializers.he_normal`](https://www.tensorflow.org/api_docs/python/tf/keras/initializers/HeNormal)

<br />

    tf.keras.initializers.HeNormal(
        seed=None
    )

Also available via the shortcut function
[`tf.keras.initializers.he_normal`](https://www.tensorflow.org/versions/r2.3/api_docs/python/tf/keras/initializers/HeNormal).

It draws samples from a truncated normal distribution centered on 0 with
`stddev = sqrt(2 / fan_in)` where `fan_in` is the number of input units in the
weight tensor.

#### Examples:

    # Standalone usage:
    initializer = tf.keras.initializers.HeNormal()
    values = initializer(shape=(2, 2))

    # Usage in a Keras layer:
    initializer = tf.keras.initializers.HeNormal()
    layer = tf.keras.layers.Dense(3, kernel_initializer=initializer)

<br />

<br />

<br />

| ## Arguments ||
|---|---|
| `seed` | A Python integer. An initializer created with a given seed will always produce the same random tensor for a given shape and dtype. |

<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))

## Methods

### `from_config`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.3.0/tensorflow/python/ops/init_ops_v2.py#L70-L90)

    @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)

<br />

<br />

<br />

| Args ||
|---|---|
| `config` | A Python dictionary. It will typically be the output of `get_config`. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| An Initializer instance. ||

<br />

### `get_config`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.3.0/tensorflow/python/keras/initializers/initializers_v2.py#L703-L704)

    get_config()

Returns the configuration of the initializer as a JSON-serializable dict.

<br />

<br />

<br />

| Returns ||
|---|---|
| A JSON-serializable Python dict. ||

<br />

### `__call__`

[View source](https://github.com/tensorflow/tensorflow/blob/v2.3.0/tensorflow/python/keras/initializers/initializers_v2.py#L387-L397)

    __call__(
        shape, dtype=None
    )

Returns a tensor object initialized as specified by the initializer.

<br />

<br />

<br />

| Args ||
|---|---|
| `shape` | Shape of the tensor. |
| `dtype` | Optional dtype of the tensor. Only floating point types are supported. If not specified, [`tf.keras.backend.floatx()`](https://www.tensorflow.org/versions/r2.3/api_docs/python/tf/keras/backend/floatx) is used, which default to `float32` unless you configured it otherwise (via [`tf.keras.backend.set_floatx(float_dtype)`](https://www.tensorflow.org/versions/r2.3/api_docs/python/tf/keras/backend/set_floatx)) |

<br />