VQC

class VQC(num_qubits=None, feature_map=None, ansatz=None, loss='cross_entropy', optimizer=None, warm_start=False, initial_point=None, callback=None, *, sampler=None)

Bases: NeuralNetworkClassifier

A convenient Variational Quantum Classifier implementation.

The variational quantum classifier (VQC) is a variational algorithm where the measured bitstrings are interpreted as the output of a classifier.

Constructs a quantum circuit and corresponding neural network, then uses it to instantiate a neural network classifier.

Labels can be passed in various formats, they can be plain labels, a one dimensional numpy array that contains integer labels like [0, 1, 2, …], or a numpy array with categorical string labels. One hot encoded labels are also supported. Internally, labels are transformed to one hot encoding and the classifier is always trained on one hot labels.

Multi-label classification is not supported. E.g., \([[1, 1, 0], [0, 1, 1], [1, 0, 1]]\).

Parameters:

• num_qubits (int | None) – The number of qubits for the underlying QNN. If None is given, the number of qubits is derived from the feature map or ansatz. If neither of those is given, raises an exception. The number of qubits in the feature map and ansatz are adjusted to this number if required.

• feature_map (QuantumCircuit | None) – The (parametrized) circuit to be used as a feature map for the underlying QNN. If None is given, the ZZFeatureMap is used if the number of qubits is larger than 1. For a single qubit classification problem the ZFeatureMap is used by default.

• ansatz (QuantumCircuit | None) – The (parametrized) circuit to be used as an ansatz for the underlying QNN. If None is given then the RealAmplitudes circuit is used.

• loss (str | Loss) – A target loss function to be used in training. Default value is cross_entropy.

• optimizer (Optimizer | Minimizer | None) – An instance of an optimizer or a callable to be used in training. Refer to Minimizer for more information on the callable protocol. When None defaults to SLSQP.

• warm_start (bool) – Use weights from previous fit to start next fit.

• initial_point (np.ndarray | None) – Initial point for the optimizer to start from.

• callback (Callable[[np.ndarray, float], None] | None) – a reference to a user’s callback function that has two parameters and returns None. The callback can access intermediate data during training. On each iteration an optimizer invokes the callback and passes current weights as an array and a computed value as a float of the objective function being optimized. This allows to track how well optimization / training process is going on.

• sampler (BaseSampler | None) – an optional Sampler primitive instance to be used by the underlying SamplerQNN neural network. If None is passed then an instance of the reference Sampler will be used.

Raises:

QiskitMachineLearningError – Needs at least one out of num_qubits, feature_map or ansatz to be given. Or the number of qubits in the feature map and/or ansatz can’t be adjusted to num_qubits.

Attributes

ansatz

Returns the used ansatz.

callback

Return the callback.

circuit

Returns the underlying quantum circuit.

feature_map

Returns the used feature map.

fit_result

Returns a resulting object from the optimization procedure. Please refer to the documentation of the OptimizerResult class for more details.

Raises:

QiskitMachineLearningError – If the model has not been fit.

initial_point

Returns current initial point

loss

Returns the underlying neural network.

neural_network

Returns the underlying neural network.

num_classes

The number of classes found in the most recent fit.

If called before fit(), this will return None.

num_qubits

Returns the number of qubits used by ansatz and feature map.

optimizer

Returns an optimizer to be used in training.

warm_start

Returns the warm start flag.

weights

Returns trained weights as a numpy array. The weights can be also queried by calling model.fit_result.x, but in this case their representation depends on the optimizer used.

Raises:

QiskitMachineLearningError – If the model has not been fit.

Methods

fit(X, y)

Fit the model to data matrix X and target(s) y.

Parameters:

• X (ndarray) – The input data.

• y (ndarray) – The target values.

Returns:

returns a trained model.

Return type:

self

Raises:

QiskitMachineLearningError – In case of invalid data (e.g. incompatible with network)

classmethod load(file_name)

Loads a model from the file. If the loaded model is not an instance of the class whose method was called, then a warning is raised. Nevertheless, the loaded model may be a valid model.

Parameters:

file_name (str) – a file name or path to load a model from.

Returns:

A loaded model.

Raises:

TypeError – if a loaded model is not an instance of the expected class.

Return type:

Any

predict(X)

Predict using the network specified to the model.

Parameters:

X (ndarray) – The input data.

Raises:

QiskitMachineLearningError – Model needs to be fit to some training data first

Returns:

The predicted classes.

Return type:

ndarray

save(file_name)

Saves this model to the specified file. Internally, the model is serialized via dill. All parameters are saved, including a primitive instance that is referenced by internal objects. That means if a model is loaded from a file and is used, for instance, for inference, the same primitive will be used even if a cloud primitive was used.

Parameters:

file_name (str) – a file name or path where to save the model.

score(X, y, sample_weight=None)

Returns a score of this model given samples and true values for the samples. In case of classification this should be mean accuracy, in case of regression the coefficient of determination \(R^2\) of the prediction.

Parameters:

• X (ndarray) – Test samples.

• y (ndarray) – True values for X.

• sample_weight (ndarray | None) – Sample weights. Default is None.

Returns:

a float score of the model.

Return type:

float