DataReuploadingClassifier#

class pyqit.models.DataReuploadingClassifier(n_features, n_qubits=1, n_layers=3, n_classes=2, measure_fn=None, measure_wires=None, device='default.qubit', shots=None, diff_method='best')[source]#

Bases: BaseQuantumModel, ClassifierMixin

Data re-uploading classifier of Perez-Salinas et al. (2020).

Every layer re-encodes the input: on each qubit it applies Rot(theta + w * x) (their Eq. 7), with x zero-padded to a multiple of three and consumed three features per rotation. With more than one qubit, a CZ chain entangles neighbouring wires between layers (their Sec. 4). There is no separate embedding, so the DataModule does not prescale; the model reads the normalized features directly.

The readout and the loss are pyqit’s, not the paper’s fidelity cost: binary reads (1 + <Z_0>) / 2, multi-class bins basis-state probabilities by index modulo n_classes.

Parameters:

  • n_features (int) – Input width. forward raises on any other width.

  • n_qubits (int, default 1)

  • n_layers (int, default 3) – Re-uploading layers.

  • n_classes (int, default 2)

  • measure_fn (callable, optional) – Defaults to measure_expval_z for binary, measure_probs otherwise.

  • measure_wires (list of int, optional) – Defaults to [0] for binary, all wires otherwise.

  • device (str, default "default.qubit")

  • shots (int, optional)

  • diff_method (str, default "best") – Passed to the QNode. "best" picks backprop on a simulator; "parameter-shift" rehearses a hardware run’s gradient cost.

References

Perez-Salinas, Cervera-Lierta, Gil-Fuster, Latorre, “Data re-uploading for a universal quantum classifier”, Quantum 4, 226 (2020). PennyLane’s “Data re-uploading classifier” demo is the reference implementation.

Examples

>>> import pyqit
>>> from pyqit.models import DataReuploadingClassifier
>>> model = DataReuploadingClassifier(n_features=2, n_qubits=1, n_layers=4)
>>> history = pyqit.Trainer(max_epochs=5).fit(model, dm)
diff_methods(X) → dict#

Differentiation method per QNode.

Parameters:

X (array-like) – One prescaled batch; only its shape matters.

Returns:

QNode name to method name.

Return type:

dict

execute_qnode(name: str, X, **custom_weights)#

Run the QNode or dense layer registered under name on a batch.

Parameters:

  • name (str) – Name passed to register_qnode.

  • X (array-like)

  • **custom_weights – Flat “<name>.<weight>” overrides; unprefixed keys are ignored. Falls back to the model’s own weights when empty.

Return type:

array-like

forward(X, **custom_weights)[source]#

Run the circuit and return class probabilities.

Parameters:

  • X (array-like) – Batch of n_features columns, normalized but not prescaled.

  • **custom_weights – Override the model’s own weights, keyed as in weights.

Returns:

Probability of class 1 for binary; a (n_samples, n_classes) probability matrix otherwise.

Return type:

array-like

get_interface()#

PennyLane QNode interface for the active backend.

classmethod get_test_params()[source]#

List constructor kwargs used to parametrize this class in the test suite.

init_weights(weight_shapes: dict) → dict#

Draw uniform [0, 1) starting weights from numpy’s global RNG.

The range matches Qiskit ML’s default initial_point and PennyLane’s template examples; uniform [0, 2pi) is the Haar-like regime where gradients vanish (McClean et al. 2018).

Call this before building the device: a PennyLane device seeded "global" consumes numpy’s RNG at construction by a device-dependent amount, so weights drawn after it differ per device for the same seed.

Parameters:

weight_shapes (dict) – Weight name to shape, as returned by an ansatz’s get_weight_shapes.

Return type:

dict

is_fitted() → bool#

Whether Trainer.fit has trained this model.

predict_step(X)#

Predict hard class labels for X.

Parameters:

X (array-like) – Input batch.

Returns:

One label per row: 0/1 for binary, argmax index for multi-class.

Return type:

array-like

register_dense(name: str, n_in: int, n_out: int, weights=None)#

Register a classical dense layer X @ weight.T + bias under name.

Lives in the same registry as the QNodes, so weights, update_weights, checkpoints and the flat-kwargs routing cover it with no further plumbing. Run it with execute_qnode.

Parameters:

  • name (str)

  • n_in (int)

  • n_out (int)

  • weights (dict, optional) – {"weight", "bias"} from init_dense_weights; drawn when omitted.

register_qnode(name: str, qnode: QNode, weight_shapes: dict, weights=None)#

Wrap qnode for the active backend and store it under name.

Parameters:

  • name (str) – Key under which the node’s weights appear in weights.

  • qnode (qml.QNode)

  • weight_shapes (dict) – Weight name to shape, as returned by an ansatz’s get_weight_shapes.

  • weights (dict, optional) – Starting weights from init_weights; drawn here when omitted, so both backends start from the same point for the same seed.

update_weights(flat_weights_dict)#

Write flat_weights_dict into the model’s own weights.

No-op under torch, where autograd owns the nn.Parameter objects directly.

Parameters:

flat_weights_dict (dict) – Keyed like weights.

weight_groups() → dict#

weights keys by group, "quantum" (QNodes) and "classical".

Empty groups are omitted. The training loops build one optimizer per group, which is what lets Trainer(learning_rate={...}) set a rate per group.

property weights#

Flat {"<qnode_name>.<weight_name>": array} dict, both backends.