<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/affine_layers.py#L433-L600) |

Densely-connected layer class with local reparameterization estimator.

Inherits From: [`VariationalLayer`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/nn/VariationalLayer), [`Layer`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/nn/Layer)

    tfp.experimental.nn.AffineVariationalReparameterizationLocal(
        input_size,
        output_size,
        kernel_initializer=None,
        bias_initializer=None,
        make_posterior_fn=https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/nn/util/make_kernel_bias_posterior_mvn_diag,
        make_prior_fn=https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/nn/util/make_kernel_bias_prior_spike_and_slab,
        posterior_value_fn=https://www.tensorflow.org/probability/api_docs/python/tfp/distributions/Distribution#sample,
        unpack_weights_fn=unpack_kernel_and_bias,
        dtype=tf.float32,
        activation_fn=None,
        seed=None,
        validate_args=False,
        name=None
    )

This layer implements the Bayesian variational inference analogue to
a dense layer by assuming the `kernel` and/or the `bias` are drawn
from distributions. By default, the layer implements a stochastic
forward pass via sampling from the kernel and bias posteriors,

    kernel, bias ~ posterior
    outputs = matmul(inputs, kernel) + bias

It uses the local reparameterization estimator \[(Kingma et al., 2015)\]\[1\],
which performs a Monte Carlo approximation of the distribution on the hidden
units induced by the `kernel` and `bias`. The default `kernel_posterior_fn`
is a normal distribution which factorizes across all elements of the weight
matrix and bias vector. Unlike \[1\]'s multiplicative parameterization, this
distribution has trainable location and scale parameters which is known as
an additive noise parameterization \[(Molchanov et al., 2017)\]\[2\].

The arguments permit separate specification of the surrogate posterior
(`q(W|x)`), prior (`p(W)`), and divergence for both the `kernel` and `bias`
distributions.

Upon being built, this layer adds losses (accessible via the `losses`
property) representing the divergences of `kernel` and/or `bias` surrogate
posteriors and their respective priors. When doing minibatch stochastic
optimization, make sure to scale this loss such that it is applied just once
per epoch (e.g. if `kl` is the sum of `losses` for each element of the batch,
you should pass `kl / num_examples_per_epoch` to your optimizer).

You can access the `kernel` and/or `bias` posterior and prior distributions
after the layer is built via the `kernel_posterior`, `kernel_prior`,
`bias_posterior` and `bias_prior` properties.

#### Examples

We illustrate a Bayesian neural network with [variational inference](https://en.wikipedia.org/wiki/Variational_Bayesian_methods),
assuming a dataset of images and length-10 one-hot `targets`.

    # Using the following substitution, see:
    tfn = tfp.experimental.nn
    help(tfn.AffineVariationalReparameterization)
    BayesAffine =  tfn.AffineVariationalReparameterizationLocal

This example uses reparameterization gradients to minimize the
Kullback-Leibler divergence up to a constant, also known as the negative
Evidence Lower Bound. It consists of the sum of two terms: the expected
negative log-likelihood, which we approximate via Monte Carlo; and the KL
divergence, which is added via regularizer terms which are arguments to the
layer.

#### References

\[1\]: Diederik Kingma, Tim Salimans, and Max Welling. Variational Dropout and
the Local Reparameterization Trick. In *Neural Information Processing
Systems* , 2015. <https://arxiv.org/abs/1506.02557>
\[2\]: Dmitry Molchanov, Arsenii Ashukha, Dmitry Vetrov. Variational Dropout
Sparsifies Deep Neural Networks. In *International Conference on Machine
Learning* , 2017. <https://arxiv.org/abs/1701.05369>

<br />

<br />

<br />

| ## Args ||
|---|---|
| `input_size` | ... |
| `output_size` | ... |
| `kernel_initializer` | ... Default value: `None` (i.e., `tfp.nn.initializers.glorot_uniform()`). |
| `bias_initializer` | ... Default value: `None` (i.e., `tf_keras.initializers.zeros()`). |
| `make_posterior_fn` | ... Default value: [`tfp.experimental.nn.util.make_kernel_bias_posterior_mvn_diag`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/nn/util/make_kernel_bias_posterior_mvn_diag). |
| `make_prior_fn` | ... Default value: [`tfp.experimental.nn.util.make_kernel_bias_prior_spike_and_slab`](https://www.tensorflow.org/probability/api_docs/python/tfp/experimental/nn/util/make_kernel_bias_prior_spike_and_slab). |
| `posterior_value_fn` | ... Default valye: `tfd.Distribution.sample` |
| `unpack_weights_fn` | Default value: `unpack_kernel_and_bias` |
| `dtype` | ... Default value: [`tf.float32`](https://www.tensorflow.org/api_docs/python/tf#float32). |
| `activation_fn` | ... Default value: `None`. |
| `seed` | ... Default value: `None` (i.e., no seed). |
| `validate_args` | ... Default value: `False`. |
| `name` | ... Default value: `None` (i.e., `'AffineVariationalFlipout'`). |

<br />

<br />

<br />

<br />

| ## Attributes ||
|---|---|
| `activation_fn` | <br /> <br /> |
| `also_track` | <br /> <br /> |
| `dtype` | <br /> <br /> |
| `name` | Returns the name of this module as passed or determined in the ctor. <br /> > [!NOTE] > **Note:** This is not the same as the `self.name_scope.name` which includes parent module names. |
| `name_scope` | Returns a [`tf.name_scope`](https://www.tensorflow.org/api_docs/python/tf/name_scope) instance for this class. |
| `non_trainable_variables` | Sequence of non-trainable variables owned by this module and its submodules. > [!NOTE] > **Note:** this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don't expect the return value to change. |
| `posterior` | <br /> |
| `posterior_value` | <br /> <br /> |
| `posterior_value_fn` | <br /> <br /> |
| `prior` | <br /> <br /> |
| `submodules` | Sequence of all sub-modules. <br /> Submodules are modules which are properties of this module, or found as properties of modules which are properties of this module (and so on). a = tf.Module() b = tf.Module() c = tf.Module() a.b = b b.c = c list(a.submodules) == [b, c] True list(b.submodules) == [c] True list(c.submodules) == [] True <br /> |
| `trainable_variables` | Sequence of trainable variables owned by this module and its submodules. <br /> > [!NOTE] > **Note:** this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don't expect the return value to change. |
| `unpack_weights_fn` | <br /> |
| `validate_args` | Python `bool` indicating possibly expensive checks are enabled. |
| `variables` | Sequence of variables owned by this module and its submodules. <br /> > [!NOTE] > **Note:** this method uses reflection to find variables on the current instance and submodules. For performance reasons you may wish to cache the result of calling this method if you don't expect the return value to change. |

## Methods

### `load`

[View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/experimental/nn/layers.py#L55-L56)

    load(
        filename
    )

### `save`

[View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/experimental/nn/layers.py#L52-L53)

    save(
        filename
    )

### `summary`

[View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/experimental/nn/layers.py#L49-L50)

    summary()

### `with_name_scope`

    @classmethod
    with_name_scope(
        method
    )

Decorator to automatically enter the module name scope.

    class MyModule(tf.Module):
      @tf.Module.with_name_scope
      def __call__(self, x):
        if not hasattr(self, 'w'):
          self.w = tf.Variable(tf.random.normal([x.shape[1], 3]))
        return tf.matmul(x, self.w)

Using the above module would produce [`tf.Variable`](https://www.tensorflow.org/api_docs/python/tf/Variable)s and [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor)s whose
names included the module name:

    mod = MyModule()
    mod(tf.ones([1, 2]))
    <tf.Tensor: shape=(1, 3), dtype=float32, numpy=..., dtype=float32)>
    mod.w
    <tf.Variable 'my_module/Variable:0' shape=(2, 3) dtype=float32,
    numpy=..., dtype=float32)>

<br />

<br />

<br />

| Args ||
|---|---|
| `method` | The method to wrap. |

<br />

<br />

<br />

<br />

| Returns ||
|---|---|
| The original method wrapped such that it enters the module's name scope. ||

<br />

### `__call__`

[View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/experimental/nn/affine_layers.py#L574-L600)

    __call__(
        x
    )

Call self as a function.