tfq.layers.State

View source on GitHub

A Layer that simulates a quantum state.

tfq.layers.State(
 backend=None, **kwargs
)

Used in the notebooks

Used in the tutorials

Given an input circuit and set of parameter values, Simulate a quantum state and output it to the Tensorflow graph.

A more common application is for determining the set of states produced by a parametrized circuit where the values of the parameters vary. Suppose we want to generate a family of states with varying degrees of entanglement ranging from separable to maximally entangled. We first define a parametrized circuit that can accomplish this

q0, q1 = cirq.GridQubit.rect(1, 2)
alpha = sympy.Symbol('alpha') # degree of entanglement between q0, q1
parametrized_bell_circuit = cirq.Circuit(
 cirq.H(q0), cirq.CNOT(q0, q1) ** alpha)

Now pass all of the alpha values desired to tfq.layers.State to compute a tensor of states corresponding to these preparation angles.

state_layer = tfq.layers.State()
alphas = tf.reshape(tf.range(0, 1.1, delta=0.5), (3, 1)) # FIXME: #805
state_layer(parametrized_bell_circuit,
 symbol_names=[alpha], symbol_values=alphas)
<tf.RaggedTensor [[0.707106, 0j, 0.707106, 0j],
[(0.707106-1.2802768623032534e-08j), 0j,
 (0.353553+0.3535534143447876j), (0.353553-0.3535533547401428j)],
[(0.707106-1.2802768623032534e-08j), 0j,
 (0.-3.0908619663705394e-08j), (0.707106+6.181723932741079e-08j)]]>

This use case can be simplified to compute the state vector produced by a fixed circuit where the values of the parameters vary. For example, this layer produces a Bell state.

q0, q1 = cirq.GridQubit.rect(1, 2)
bell_circuit = cirq.Circuit(cirq.H(q0), cirq.CNOT(q0, q1))
state_layer = tfq.layers.State()
state_layer(bell_circuit)
<tf.RaggedTensor [[(0.707106-1.2802768623032534e-08j),
 0j,
 (0.-3.0908619663705394e-08j),
 (0.707106+6.181723932741079e-08j)]]>

Not specifying symbol_names or symbol_values indicates that the circuit(s) does not contain any sympy.Symbols inside of it and tfq won't look for any symbols to resolve.

tfq.layers.State also allows for a more complicated input signature wherein a different (possibly parametrized) circuit is used to prepare a state for each batch of input parameters. This might be useful when the State layer is being used to generate entirely different families of states. Suppose we want to generate a stream of states that are either computational basis states or 'diagonal' basis states (as in the BB84 QKD protocol). The circuits to prepare these states are:

q0 = cirq.GridQubit(0, 0)
bitval = sympy.Symbol('bitval')
computational_circuit = cirq.Circuit(cirq.X(q0) ** bitval)
diagonal_circuit = cirq.Circuit(cirq.X(q0) ** bitval, cirq.H(q0))

Now a stream of random classical bit values can be encoded into one of these bases by preparing a state layer and passing in the bit values accompanied by their preparation circuits

qkd_layer = tfq.layers.State()
bits = [[1], [1], [0], [0]]
states_to_send = [computational_circuit,
 diagonal_circuit,
 diagonal_circuit,
 computational_circuit]
qkd_states = qkd_layer(
 states_to_send, symbol_names=[bitval], symbol_values=bits)
# The third state was a '0' prepared in the diagonal basis:
qkd_states
<tf.RaggedTensor [[-4.371138828673793e-08j, (1+4.371138828673793e-08j)],
[(0.707106+3.0908619663705394e-08j), (-0.707106-1.364372508305678e-07j)],
[(0.707106-1.2802768623032534e-08j), (0.707106+3.0908619663705394e-08j)],
[(1+0j), 0j]]>

Args

backend Optional Backend to use to simulate this state. Defaults to the native TensorFlow Quantum state vector simulator, however users may also specify a preconfigured cirq execution object to use instead, which must inherit cirq.SimulatesFinalState. Note that C++ Density Matrix simulation is not yet supported so to do Density Matrix simulation please use cirq.DensityMatrixSimulator.

Attributes

compute_dtype The dtype of the computations performed by the layer.
dtype Alias of layer.variable_dtype.
dtype_policy

input Retrieves the input tensor(s) of a symbolic operation.

Only returns the tensor(s) corresponding to the first time the operation was called.

input_dtype The dtype layer inputs should be converted to.
input_spec

losses List of scalar losses from add_loss, regularizers and sublayers.
metrics List of all metrics.
metrics_variables List of all metric variables.
non_trainable_variables List of all non-trainable layer state.

This extends layer.non_trainable_weights to include all state used by the layer including state for metrics and SeedGenerators.

non_trainable_weights List of all non-trainable weight variables of the layer.

These are the weights that should not be updated by the optimizer during training. Unlike, layer.non_trainable_variables this excludes metric state and random seeds.

output Retrieves the output tensor(s) of a layer.

Only returns the tensor(s) corresponding to the first time the operation was called.

path The path of the layer.

If the layer has not been built yet, it will be None.

quantization_mode The quantization mode of this layer, None if not quantized.
supports_masking Whether this layer supports computing a mask using compute_mask.
trainable Settable boolean, whether this layer should be trainable or not.
trainable_variables List of all trainable layer state.

This is equivalent to layer.trainable_weights.

trainable_weights List of all trainable weight variables of the layer.

These are the weights that get updated by the optimizer during training.

variable_dtype The dtype of the state (weights) of the layer.
variables List of all layer state, including random seeds.

This extends layer.weights to include all state used by the layer including SeedGenerators.

Note that metrics variables are not included here, use metrics_variables to visit all the metric variables.

weights List of all weight variables of the layer.

Unlike, layer.variables this excludes metric state and random seeds.

Methods

add_loss

add_loss(
 loss
)

Can be called inside of the call() method to add a scalar loss.

Example:

classMyLayer(Layer):
 ...
 defcall(self, x):
 self.add_loss(ops.sum(x))
 return x

add_metric

add_metric(
 *args, **kwargs
)

add_variable

add_variable(
 shape,
 initializer,
 dtype=None,
 trainable=True,
 autocast=True,
 regularizer=None,
 constraint=None,
 name=None
)

Add a weight variable to the layer.

Alias of add_weight().

add_weight

add_weight(
 shape=None,
 initializer=None,
 dtype=None,
 trainable=True,
 autocast=True,
 regularizer=None,
 constraint=None,
 aggregation='none',
 overwrite_with_gradient=False,
 name=None
)

Add a weight variable to the layer.

Args
shape Shape tuple for the variable. Must be fully-defined (no None entries). Defaults to () (scalar) if unspecified.
initializer Initializer object to use to populate the initial variable value, or string name of a built-in initializer (e.g. "random_normal"). If unspecified, defaults to "glorot_uniform" for floating-point variables and to "zeros" for all other types (e.g. int, bool).
dtype Dtype of the variable to create, e.g. "float32". If unspecified, defaults to the layer's variable dtype (which itself defaults to "float32" if unspecified).
trainable Boolean, whether the variable should be trainable via backprop or whether its updates are managed manually. Defaults to True.
autocast Boolean, whether to autocast layers variables when accessing them. Defaults to True.
regularizer Regularizer object to call to apply penalty on the weight. These penalties are summed into the loss function during optimization. Defaults to None.
constraint Contrainst object to call on the variable after any optimizer update, or string name of a built-in constraint. Defaults to None.
aggregation Optional string, one of None, "none", "mean", "sum" or "only_first_replica". Annotates the variable with the type of multi-replica aggregation to be used for this variable when writing custom data parallel training loops. Defaults to "none".
overwrite_with_gradient Boolean, whether to overwrite the variable with the computed gradient. This is useful for float8 training. Defaults to False.
name String name of the variable. Useful for debugging purposes.

build

build(
 input_shape
)

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.

call

View source 

call(
 inputs, *, symbol_names=None, symbol_values=None
)

Keras call function.

Input options
inputs, symbol_names, symbol_values: see input_checks.expand_circuits

Output shape
tf.RaggedTensor with shape: [batch size of symbol_values, ] or [number of circuits, ]

compute_mask

compute_mask(
 inputs, previous_mask
)

compute_output_shape

compute_output_shape(
 *args, **kwargs
)

compute_output_spec

compute_output_spec(
 *args, **kwargs
)

count_params

count_params()

Count the total number of scalars composing the weights.

Returns
An integer count.

from_config

@classmethod
from_config(
 config
)

Creates an operation from its config.

This method is the reverse of get_config, capable of instantiating the same operation from the config dictionary.

if "dtype" in config and isinstance(config["dtype"], dict):
 policy = dtype_policies.deserialize(config["dtype"])

Args
config A Python dictionary, typically the output of get_config.

Returns
An operation 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 Keras attempts to load its value upon model loading.

Returns
A dict containing the input shape associated with the layer.

get_config

get_config()

Returns the config of the object.

An object config is a Python dictionary (serializable) containing the information needed to re-instantiate it.

get_weights

get_weights()

Return the values of layer.weights 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().

Args
store Dict from which the state of the model will be loaded.

quantize

quantize(
 mode, type_check=True
)

quantized_build

quantized_build(
 input_shape, mode
)

quantized_call

quantized_call(
 *args, **kwargs
)

rematerialized_call

rematerialized_call(
 layer_call, *args, **kwargs
)

Enable rematerialization dynamically for layer's call method.

Args
layer_call The original call method of a layer.

Returns
Rematerialized layer's call method.

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 values of layer.weights from a list of NumPy arrays.

stateless_call

stateless_call(
 trainable_variables,
 non_trainable_variables,
 *args,
 return_losses=False,
 **kwargs
)

Call the layer without any side effects.

Args
trainable_variables List of trainable variables of the model.
non_trainable_variables List of non-trainable variables of the model.
*args Positional arguments to be passed to call().
return_losses If True, stateless_call() will return the list of losses created during call() as part of its return values.
**kwargs Keyword arguments to be passed to call().

Returns
A tuple. By default, returns (outputs, non_trainable_variables). If return_losses = True, then returns (outputs, non_trainable_variables, losses).

Example:

model = ...
data = ...
trainable_variables = model.trainable_variables
non_trainable_variables = model.non_trainable_variables
# Call the model with zero side effects
outputs, non_trainable_variables = model.stateless_call(
 trainable_variables,
 non_trainable_variables,
 data,
)
# Attach the updated state to the model
# (until you do this, the model is still in its pre-call state).
for ref_var, value in zip(
 model.non_trainable_variables, non_trainable_variables
):
 ref_var.assign(value)

symbolic_call

symbolic_call(
 *args, **kwargs
)

__call__

__call__(
 *args, **kwargs
)

Call self as a function.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2026年01月02日 UTC.