|---|
| [ View source on GitHub](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/layers/distribution_layer.py#L1765-L1945) |
A VariationalGaussianProcess Layer.
Inherits From: [`DistributionLambda`](https://www.tensorflow.org/probability/api_docs/python/tfp/layers/DistributionLambda)
#### View aliases
**Main aliases**
[`tfp.layers.distribution_layer.VariationalGaussianProcess`](https://www.tensorflow.org/probability/api_docs/python/tfp/layers/VariationalGaussianProcess)
tfp.layers.VariationalGaussianProcess(
num_inducing_points,
kernel_provider,
event_shape=(1,),
inducing_index_points_initializer=None,
unconstrained_observation_noise_variance_initializer=tf_keras.initializers.constant(-10.0),
variational_inducing_observations_scale_initializer=None,
mean_fn=None,
jitter=1e-06,
convert_to_tensor_fn=https://www.tensorflow.org/probability/api_docs/python/tfp/distributions/Distribution#sample,
name=None
)
### Used in the notebooks
| Used in the tutorials |
|---|
| - [TFP Probabilistic Layers: Regression](https://www.tensorflow.org/probability/examples/Probabilistic_Layers_Regression) |
Create a VariationalGaussianProcess distribtuion whose `index_points` are the
inputs to the layer. Parameterized by number of inducing points and a
`kernel_provider`, which should be a `tf_keras.Layer` with an @property that
late-binds variable parameters to a
`tfp.positive_semidefinite_kernel.PositiveSemidefiniteKernel` instance (this
requirement has to do with the way that variables must be created in a keras
model). The `mean_fn` is an optional argument which, if omitted, will be
automatically configured to be a constant function with trainable variable
output.
| ## Args ||
|---|---|
| `num_inducing_points` | number of inducing points in the VariationalGaussianProcess distribution. |
| `kernel_provider` | a `Layer` instance equipped with an @property, which yields a `PositiveSemidefiniteKernel` instance. The latter is used to parameterize the constructed VariationalGaussianProcess distribution returned by calling the layer. |
| `event_shape` | the shape of the output of the layer. This translates to a batch of underlying VariationalGaussianProcess distribtuions. For example, `event_shape = [3]` means we are modeling a batch of 3 distributions over functions. We can think of this as a distrbution over 3-dimensional vector-valued functions. |
| `inducing_index_points_initializer` | a `tf_keras.initializer.Initializer` used to initialize the trainable `inducing_index_points` variables. Training VGP's is pretty sensitive to choice of initial inducing index point locations. A reasonable heuristic is to scatter them near the data, not too close to each other. |
| `unconstrained_observation_noise_variance_initializer` | a `tf_keras.initializer.Initializer` used to initialize the unconstrained observation noise variable. The observation noise variance is computed from this variable via the [`tf.nn.softplus`](https://www.tensorflow.org/api_docs/python/tf/math/softplus) function. |
| `variational_inducing_observations_scale_initializer` | a `tf_keras.initializer.Initializer` used to initialize the variational inducing observations scale. |
| `mean_fn` | a callable that maps layer inputs to mean function values. Passed to the mean_fn parameter of VariationalGaussianProcess distribution. If omitted, defaults to a constant function with trainable variable value. |
| `jitter` | a small term added to the diagonal of various kernel matrices for numerical stability. |
| `convert_to_tensor_fn` | Python `callable` that takes a `tfd.Distribution` instance and returns a [`tf.Tensor`](https://www.tensorflow.org/api_docs/python/tf/Tensor)-like object. For examples, see `class` docstring. |
| `name` | name to give to this layer and the scope of ops and variables it contains. |
| ## Attributes ||
|---|---|
| `activity_regularizer` | Optional regularizer function for the output of this layer. |
| `compute_dtype` | The dtype of the layer's computations.
This is equivalent to `Layer.dtype_policy.compute_dtype`. Unless mixed precision is used, this is the same as [`Layer.dtype`](https://www.tensorflow.org/api_docs/python/tf/keras/Layer#dtype), the dtype of the weights. Layers automatically cast their inputs to the compute dtype, which causes computations and the output to be in the compute dtype as well. This is done by the base Layer class in [`Layer.call`](https://www.tensorflow.org/probability/oryx/api_docs/python/oryx/core/state/Module#__call__), so you do not have to insert these casts if implementing your own layer. Layers often perform certain internal computations in higher precision when `compute_dtype` is float16 or bfloat16 for numeric stability. The output will still typically be float16 or bfloat16 in such cases. |
| `dtype` | The dtype of the layer weights.
This is equivalent to `Layer.dtype_policy.variable_dtype`. Unless mixed precision is used, this is the same as [`Layer.compute_dtype`](https://www.tensorflow.org/api_docs/python/tf/keras/Layer#compute_dtype), the dtype of the layer's computations. |
| `dtype_policy` | The dtype policy associated with this layer.
This is an instance of a [`tf.keras.mixed_precision.Policy`](https://www.tensorflow.org/api_docs/python/tf/keras/DTypePolicy). |
| `dynamic` | Whether the layer is dynamic (eager-only); set in the constructor. |
| `input` | Retrieves the input tensor(s) of a layer.
Only applicable if the layer has exactly one input, i.e. if it is connected to one incoming layer. |
| `input_spec` | `InputSpec` instance(s) describing the input format for this layer.
When you create a layer subclass, you can set `self.input_spec` to enable the layer to run input compatibility checks when it is called. Consider a `Conv2D` layer: it can only be called on a single input tensor of rank 4. As such, you can set, in `__init__()`: self.input_spec = tf.keras.layers.InputSpec(ndim=4) Now, if you try to call the layer on an input that isn't rank 4 (for instance, an input of shape `(2,)`, it will raise a nicely-formatted error: ValueError: Input 0 of layer conv2d is incompatible with the layer: expected ndim=4, found ndim=1. Full shape received: [2] Input checks that can be specified via `input_spec` include: - Structure (e.g. a single input, a list of 2 inputs, etc) - Shape - Rank (ndim) - Dtype For more information, see [`tf.keras.layers.InputSpec`](https://www.tensorflow.org/api_docs/python/tf/keras/InputSpec). |
| `losses` | List of losses added using the `add_loss()` API.
Variable regularization tensors are created when this property is accessed, so it is eager safe: accessing `losses` under a [`tf.GradientTape`](https://www.tensorflow.org/api_docs/python/tf/GradientTape) will propagate gradients back to the corresponding variables. class MyLayer(tf.keras.layers.Layer): def call(self, inputs): self.add_loss(tf.abs(tf.reduce_mean(inputs))) return inputs l = MyLayer() l(np.ones((10, 1))) l.losses [1.0] inputs = tf.keras.Input(shape=(10,)) x = tf.keras.layers.Dense(10)(inputs) outputs = tf.keras.layers.Dense(1)(x) model = tf.keras.Model(inputs, outputs) # Activity regularization. len(model.losses) 0 model.add_loss(tf.abs(tf.reduce_mean(x))) len(model.losses) 1 inputs = tf.keras.Input(shape=(10,)) d = tf.keras.layers.Dense(10, kernel_initializer='ones') x = d(inputs) outputs = tf.keras.layers.Dense(1)(x) model = tf.keras.Model(inputs, outputs) # Weight regularization. model.add_loss(lambda: tf.reduce_mean(d.kernel)) model.losses []
|
| `metrics` | List of metrics attached to the layer. |
| `name` | Name of the layer (string), set in the constructor. |
| `name_scope` | Returns a [`tf.name_scope`](https://www.tensorflow.org/api_docs/python/tf/name_scope) instance for this class. |
| `non_trainable_weights` | List of all non-trainable weights tracked by this layer.
Non-trainable weights are *not* updated during training. They are expected to be updated manually in `call()`. |
| `output` | Retrieves the output tensor(s) of a layer.
Only applicable if the layer has exactly one output, i.e. if it is connected to one incoming layer. |
| `submodules` | Sequence of all sub-modules.
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
|
| `supports_masking` | Whether this layer supports computing a mask using `compute_mask`. |
| `trainable` |
|
| `trainable_weights` | List of all trainable weights tracked by this layer.
Trainable weights are updated via gradient descent during training. |
| `variable_dtype` | Alias of [`Layer.dtype`](https://www.tensorflow.org/api_docs/python/tf/keras/Layer#dtype), the dtype of the weights. |
| `weights` | Returns the list of all layer variables/weights. |
## Methods
### `add_loss`
add_loss(
losses, **kwargs
)
Add loss tensor(s), potentially dependent on layer inputs.
Some losses (for instance, activity regularization losses) may be
dependent on the inputs passed when calling a layer. Hence, when reusing
the same layer on different inputs `a` and `b`, some entries in
`layer.losses` may be dependent on `a` and some on `b`. This method
automatically keeps track of dependencies.
This method can be used inside a subclassed layer or model's `call`
function, in which case `losses` should be a Tensor or list of Tensors.
#### Example:
class MyLayer(tf.keras.layers.Layer):
def call(self, inputs):
self.add_loss(tf.abs(tf.reduce_mean(inputs)))
return inputs
The same code works in distributed training: the input to `add_loss()`
is treated like a regularization loss and averaged across replicas
by the training loop (both built-in [`Model.fit()`](https://www.tensorflow.org/api_docs/python/tf/keras/Model#fit) and compliant custom
training loops).
The `add_loss` method can also be called directly on a Functional Model
during construction. In this case, any loss Tensors passed to this Model
must be symbolic and be able to be traced back to the model's `Input`s.
These losses become part of the model's topology and are tracked in
`get_config`.
#### Example:
inputs = tf.keras.Input(shape=(10,))
x = tf.keras.layers.Dense(10)(inputs)
outputs = tf.keras.layers.Dense(1)(x)
model = tf.keras.Model(inputs, outputs)
# Activity regularization.
model.add_loss(tf.abs(tf.reduce_mean(x)))
If this is not the case for your loss (if, for example, your loss
references a `Variable` of one of the model's layers), you can wrap your
loss in a zero-argument lambda. These losses are not tracked as part of
the model's topology since they can't be serialized.
#### Example:
inputs = tf.keras.Input(shape=(10,))
d = tf.keras.layers.Dense(10)
x = d(inputs)
outputs = tf.keras.layers.Dense(1)(x)
model = tf.keras.Model(inputs, outputs)
# Weight regularization.
model.add_loss(lambda: tf.reduce_mean(d.kernel))
| Args ||
|---|---|
| `losses` | Loss tensor, or list/tuple of tensors. Rather than tensors, losses may also be zero-argument callables which create a loss tensor. |
| `**kwargs` | Used for backwards compatibility only. |
### `build`
[View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/layers/distribution_layer.py#L1863-L1912)
build(
input_shape
)
Creates the variables of the layer (for subclass implementers).
This is a method that implementers of subclasses of `Layer` or `Model`
can override if they need a state-creation step in-between
layer instantiation and layer call. It is invoked automatically before
the first execution of `call()`.
This is typically used to create the weights of `Layer` subclasses
(at the discretion of the subclass implementer).
| Args ||
|---|---|
| `input_shape` | Instance of `TensorShape`, or list of instances of `TensorShape` if the layer expects a list of inputs (one instance per input). |
### `build_from_config`
build_from_config(
config
)
Builds the layer's states with the supplied config dict.
By default, this method calls the `build(config["input_shape"])` method,
which creates weights based on the layer's input shape in the supplied
config. If your config contains other information needed to load the
layer's state, you should override this method.
| Args ||
|---|---|
| `config` | Dict containing the input shape associated with this layer. |
### `compute_mask`
compute_mask(
inputs, mask=None
)
Computes an output mask tensor.
| Args ||
|---|---|
| `inputs` | Tensor or list of tensors. |
| `mask` | Tensor or list of tensors. |
| Returns ||
|---|---|
| None or a tensor (or list of tensors, one per output tensor of the layer). ||
### `compute_output_shape`
compute_output_shape(
input_shape
)
### `count_params`
count_params()
Count the total number of scalars composing the weights.
| Returns ||
|---|---|
| An integer count. ||
| Raises ||
|---|---|
| `ValueError` | if the layer isn't yet built (in which case its weights aren't yet defined). |
### `from_config`
@classmethod
from_config(
config, custom_objects=None
)
Creates a layer from its config.
This method is the reverse of `get_config`,
capable of instantiating the same layer from the config
dictionary. It does not handle layer connectivity
(handled by Network), nor weights (handled by `set_weights`).
| Args ||
|---|---|
| `config` | A Python dictionary, typically the output of get_config. |
| Returns ||
|---|---|
| A layer instance. ||
### `get_build_config`
get_build_config()
Returns a dictionary with the layer's input shape.
This method returns a config dict that can be used by
`build_from_config(config)` to create all states (e.g. Variables and
Lookup tables) needed by the layer.
By default, the config only contains the input shape that the layer
was built with. If you're writing a custom layer that creates state in
an unusual way, you should override this method to make sure this state
is already created when TF-Keras attempts to load its value upon model
loading.
| Returns ||
|---|---|
| A dict containing the input shape associated with the layer. ||
### `get_config`
[View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/layers/distribution_layer.py#L239-L276)
get_config()
Returns the config of this layer.
This Layer's `make_distribution_fn` is serialized via a library built on
Python pickle. This serialization of Python functions is provided for
convenience, but:
1. The use of this format for long-term storage of models is discouraged.
In particular, it may not be possible to deserialize in a different
version of Python.
2. While serialization is generally supported for lambdas, local
functions, and static methods (and closures over these constructs),
complex functions may fail to serialize.
3. `Tensor` objects (and functions referencing `Tensor` objects) can only
be serialized when the tensor value is statically known. (Such Tensors
are serialized as numpy arrays.)
Instead of relying on [`DistributionLambda.get_config`](https://www.tensorflow.org/probability/api_docs/python/tfp/layers/DistributionLambda#get_config), consider subclassing
`DistributionLambda` and directly implementing Keras serialization via
`get_config` / `from_config`.
> [!NOTE]
> **Note:** At the moment, `DistributionLambda` can only be serialized if the `convert_to_tensor_fn` is a serializable Keras object (i.e., implements `get_config`) or one of the standard values:
- [`Distribution.sample`](https://www.tensorflow.org/probability/api_docs/python/tfp/distributions/Distribution#sample) (or `"sample"`)
- [`Distribution.mean`](https://www.tensorflow.org/probability/api_docs/python/tfp/distributions/Distribution#mean) (or `"mean"`)
- [`Distribution.mode`](https://www.tensorflow.org/probability/api_docs/python/tfp/distributions/Distribution#mode) (or `"mode"`)
- [`Distribution.stddev`](https://www.tensorflow.org/probability/api_docs/python/tfp/distributions/Distribution#stddev) (or `"stddev"`)
- [`Distribution.variance`](https://www.tensorflow.org/probability/api_docs/python/tfp/distributions/Distribution#variance) (or `"variance"`)
### `get_weights`
get_weights()
Returns the current weights of the layer, as NumPy arrays.
The weights of a layer represent the state of the layer. This function
returns both trainable and non-trainable weight values associated with
this layer as a list of NumPy arrays, which can in turn be used to load
state into similarly parameterized layers.
For example, a `Dense` layer returns a list of two values: the kernel
matrix and the bias vector. These can be used to set the weights of
another `Dense` layer:
layer_a = tf.keras.layers.Dense(1,
kernel_initializer=tf.constant_initializer(1.))
a_out = layer_a(tf.convert_to_tensor([[1., 2., 3.]]))
layer_a.get_weights()
[array([[1.],
[1.],
[1.]], dtype=float32), array([0.], dtype=float32)]
layer_b = tf.keras.layers.Dense(1,
kernel_initializer=tf.constant_initializer(2.))
b_out = layer_b(tf.convert_to_tensor([[10., 20., 30.]]))
layer_b.get_weights()
[array([[2.],
[2.],
[2.]], dtype=float32), array([0.], dtype=float32)]
layer_b.set_weights(layer_a.get_weights())
layer_b.get_weights()
[array([[1.],
[1.],
[1.]], dtype=float32), array([0.], dtype=float32)]
| Returns ||
|---|---|
| Weights values as a list of NumPy arrays. ||
### `load_own_variables`
load_own_variables(
store
)
Loads the state of the layer.
You can override this method to take full control of how the state of
the layer is loaded upon calling [`keras.models.load_model()`](https://www.tensorflow.org/api_docs/python/tf/keras/models/load_model).
| Args ||
|---|---|
| `store` | Dict from which the state of the model will be loaded. |
### `new`
[View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/layers/distribution_layer.py#L1914-L1945)
@staticmethod
new(
x,
kernel_provider,
event_shape,
inducing_index_points,
mean_fn,
variational_inducing_observations_loc,
variational_inducing_observations_scale,
observation_noise_variance,
jitter=1e-06,
name=None
)
### `save_own_variables`
save_own_variables(
store
)
Saves the state of the layer.
You can override this method to take full control of how the state of
the layer is saved upon calling `model.save()`.
| Args ||
|---|---|
| `store` | Dict where the state of the model will be saved. |
### `set_weights`
set_weights(
weights
)
Sets the weights of the layer, from NumPy arrays.
The weights of a layer represent the state of the layer. This function
sets the weight values from numpy arrays. The weight values should be
passed in the order they are created by the layer. Note that the layer's
weights must be instantiated before calling this function, by calling
the layer.
For example, a `Dense` layer returns a list of two values: the kernel
matrix and the bias vector. These can be used to set the weights of
another `Dense` layer:
layer_a = tf.keras.layers.Dense(1,
kernel_initializer=tf.constant_initializer(1.))
a_out = layer_a(tf.convert_to_tensor([[1., 2., 3.]]))
layer_a.get_weights()
[array([[1.],
[1.],
[1.]], dtype=float32), array([0.], dtype=float32)]
layer_b = tf.keras.layers.Dense(1,
kernel_initializer=tf.constant_initializer(2.))
b_out = layer_b(tf.convert_to_tensor([[10., 20., 30.]]))
layer_b.get_weights()
[array([[2.],
[2.],
[2.]], dtype=float32), array([0.], dtype=float32)]
layer_b.set_weights(layer_a.get_weights())
layer_b.get_weights()
[array([[1.],
[1.],
[1.]], dtype=float32), array([0.], dtype=float32)]
| Args ||
|---|---|
| `weights` | a list of NumPy arrays. The number of arrays and their shape must match number of the dimensions of the weights of the layer (i.e. it should match the output of `get_weights`). |
| Raises ||
|---|---|
| `ValueError` | If the provided weights list does not match the layer's specifications. |
### `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]))
mod.w
| Args ||
|---|---|
| `method` | The method to wrap. |
| Returns ||
|---|---|
| The original method wrapped such that it enters the module's name scope. ||
### `__call__`
[View source](https://github.com/tensorflow/probability/blob/v0.25.0/tensorflow_probability/python/layers/distribution_layer.py#L219-L224)
__call__(
inputs, *args, **kwargs
)
Wraps `call`, applying pre- and post-processing steps.
| Args ||
|---|---|
| `*args` | Positional arguments to be passed to `self.call`. |
| `**kwargs` | Keyword arguments to be passed to `self.call`. |
| Returns ||
|---|---|
| Output tensor(s). ||
| Note ||
|---|---|
|
- The following optional keyword arguments are reserved for specific uses: - `training`: Boolean scalar tensor of Python boolean indicating whether the `call` is meant for training or inference. - `mask`: Boolean input mask. - If the layer's `call` method takes a `mask` argument (as some Keras layers do), its default value will be set to the mask generated for `inputs` by the previous layer (if `input` did come from a layer that generated a corresponding mask, i.e. if it came from a TF-Keras layer with masking support. - If the layer is not built, the method will call `build`. ||
| Raises ||
|---|---|
| `ValueError` | if the layer's `call` method returns None (an invalid value). |
| `RuntimeError` | if `super().__init__()` was not called in the constructor. |