tfq.layers.PQC

View source on GitHub

Parametrized Quantum Circuit (PQC) Layer.

tfq.layers.PQC(
    model_circuit,
    operators,
    *,
    repetitions=None,
    backend='noiseless',
    differentiator=None,
    initializer=tf.keras.initializers.RandomUniform(0, 2 * np.pi),
    regularizer=None,
    constraint=None,
    **kwargs
)

Used in the notebooks

This layer is for training parameterized quantum models. Given a parameterized circuit, this layer initializes the parameters and manages them in a Keras native way.

We start by defining a simple quantum circuit on one qubit. This circuit parameterizes an arbitrary rotation on the Bloch sphere in terms of the three angles a, b, and c:

q = cirq.GridQubit(0, 0)
(a, b, c) = sympy.symbols("a b c")
circuit = cirq.Circuit(
    cirq.rz(a)(q),
    cirq.rx(b)(q),
    cirq.rz(c)(q),
    cirq.rx(-b)(q),
    cirq.rz(-a)(q)
)

In order to extract information from our circuit, we must apply measurement operators. For now we choose to make a Z measurement. In order to observe an output, we must also feed our model quantum data (NOTE: quantum data means quantum circuits with no free parameters). Though the output values will depend on the default random initialization of the angles in our model, one will be the negative of the other since cirq.X(q) causes a bit flip:

outputs = tfq.layers.PQC(circuit, cirq.Z(q))
quantum_data = tfq.convert_to_tensor([
    cirq.Circuit(),
    cirq.Circuit(cirq.X(q))
])
res = outputs(quantum_data)
res
<tf.Tensor: id=577, shape=(2, 1), dtype=float32, numpy=
array([[ 0.8722095],
       [-0.8722095]], dtype=float32)>

We can also choose to measure the three pauli matrices, sufficient to fully characterize the operation of our model, or choose to simulate sampled expectation values by specifying a number of measurement shots (repetitions) to average over. Notice that using only 200 repetitions introduces variation between the two rows of data, due to the probabilistic nature of measurement.

measurement = [cirq.X(q), cirq.Y(q), cirq.Z(q)]
outputs = tfq.layers.PQC(circuit, measurement, repetitions=200)
quantum_data = tfq.convert_to_tensor([
    cirq.Circuit(),
    cirq.Circuit(cirq.X(q))
])
res = outputs(quantum_data)
res
<tf.Tensor: id=808, shape=(2, 3), dtype=float32, numpy=
array([[-0.38,  0.9 ,  0.14],
       [ 0.19, -0.95, -0.35]], dtype=float32)>

A value for backend can also be supplied in the layer constructor arguments to indicate which supported backend you would like to use. A value for differentiator can also be supplied in the constructor to indicate the differentiation scheme this PQC layer should use. Here's how you would take the gradients of the above example using a cirq.Simulator backend (which is slower than the default backend='noiseless' which uses C++):

q = cirq.GridQubit(0, 0)
(a, b, c) = sympy.symbols("a b c")
circuit = cirq.Circuit(
    cirq.rz(a)(q),
    cirq.rx(b)(q),
    cirq.rz(c)(q),
    cirq.rx(-b)(q),
    cirq.rz(-a)(q)
)
measurement = [cirq.X(q), cirq.Y(q), cirq.Z(q)]
outputs = tfq.layers.PQC(
    circuit,
    measurement,
    repetitions=5000,
    backend=cirq.Simulator(),
    differentiator=tfq.differentiators.ParameterShift())
quantum_data = tfq.convert_to_tensor([
    cirq.Circuit(),
    cirq.Circuit(cirq.X(q))
])
res = outputs(quantum_data)
res
<tf.Tensor: id=891, shape=(2, 3), dtype=float32, numpy=
array([[-0.5956, -0.2152,  0.7756],
       [ 0.5728,  0.1944, -0.7848]], dtype=float32)>

Lastly, like all layers in TensorFlow the PQC layer can be called on any tf.Tensor as long as it is the right shape. This means you could replace replace quantum_data with values fed in from a tf.keras.Input.

self.input_spec = tf.keras.layers.InputSpec(ndim=4)

ValueError: Input 0 of layer conv2d is incompatible with the layer:
expected ndim=4, found ndim=1. Full shape received: [2]

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
[<tf.Tensor: shape=(), dtype=float32, numpy=1.0>]

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

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() 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 Inputs. 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))

build

View source

build(
    input_shape
)

Keras build function.

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.

compute_mask

compute_mask(
    inputs, mask=None
)

Computes an output mask tensor.

compute_output_shape

compute_output_shape(
    input_shape
)

Computes the output shape of the layer.

This method will cause the layer's state to be built, if that has not happened before. This requires that the layer will later be used with inputs that match the input shape provided here.

count_params

count_params()

Count the total number of scalars composing the weights.

from_config

@classmethod
from_config(
    config
)

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).

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.

get_config

get_config()

Returns the config of the layer.

A layer config is a Python dictionary (serializable) containing the configuration of a layer. The same layer can be reinstantiated later (without its trained weights) from this configuration.

The config of a layer does not include connectivity information, nor the layer class name. These are handled by Network (one layer of abstraction above).

Note that get_config() does not guarantee to return a fresh copy of dict every time it is called. The callers should make a copy of the returned dict if they want to modify it.

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)]

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().

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().

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)]

symbol_values

View source

symbol_values()

Returns a Python dict containing symbol name, value pairs.

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.Variables and tf.Tensors 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)>

__call__

__call__(
    *args, **kwargs
)

Wraps call, applying pre- and post-processing steps.