# tf.initializers.variance_scaling

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/init_ops.py#L451-L542) |

Initializer capable of adapting its scale to the shape of weights tensors.

Inherits From: [`Initializer`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/keras/initializers/Initializer)

#### View aliases


**Main aliases**

[`tf.keras.initializers.VarianceScaling`](https://www.tensorflow.org/api_docs/python/tf/keras/initializers/VarianceScaling), \`tf.variance_scaling_initializer\`
**Compat aliases for migration**

See
[Migration guide](https://www.tensorflow.org/guide/migrate) for
more details.

[`tf.compat.v1.initializers.variance_scaling`](https://www.tensorflow.org/api_docs/python/tf/compat/v1/keras/initializers/VarianceScaling), [`tf.compat.v1.keras.initializers.VarianceScaling`](https://www.tensorflow.org/api_docs/python/tf/compat/v1/keras/initializers/VarianceScaling), [`tf.compat.v1.variance_scaling_initializer`](https://www.tensorflow.org/api_docs/python/tf/compat/v1/keras/initializers/VarianceScaling)

<br />

    tf.initializers.variance_scaling(
        scale=1.0, mode='fan_in', distribution='truncated_normal', seed=None,
        dtype=tf.dtypes.float32
    )

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 \[-limit, limit\], with `limit = sqrt(3 * scale / n)`.

<br />

<br />

<br />

| ## Args ||
|---|---|
| `scale` | Scaling factor (positive float). |
| `mode` | One of "fan_in", "fan_out", "fan_avg". |
| `distribution` | Random distribution to use. One of "normal", "uniform". |
| `seed` | A Python integer. Used to create random seeds. See [`tf.compat.v1.set_random_seed`](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/random/set_random_seed) for behavior. |
| `dtype` | Default data type, used if no `dtype` argument is provided when calling the initializer. Only floating point types are supported. |

<br />

<br />

<br />

<br />

| ## Raises ||
|---|---|
| `ValueError` | In case of an invalid value for the "scale", mode" or "distribution" arguments. |

<br />

## Methods

### `from_config`

[View source](https://github.com/tensorflow/tensorflow/blob/v1.15.0/tensorflow/python/ops/init_ops.py#L78-L97)

    @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/v1.15.0/tensorflow/python/ops/init_ops.py#L535-L542)

    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/v1.15.0/tensorflow/python/ops/init_ops.py#L508-L533)

    __call__(
        shape, dtype=None, partition_info=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. If not provided use the initializer dtype. |
| `partition_info` | Optional information about the possible partitioning of a tensor. |

<br />