BaseModel#

class pyqit.models.BaseModel[source]#

Bases: _PyQitObject

Base class for all trainable models in PyQit.

Holds the weight registry: layers registered under a name, run with execute_qnode, and exposed as a flat dict keyed “<layer_name>.<weight_name>” on both backends. Classical layers register here with register_dense; BaseQuantumModel adds register_qnode.

execute_qnode(name: str, X, **custom_weights)[source]#

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

abstractmethod forward(X)[source]#

Run the model on a batch and return its raw output.

is_fitted() → bool[source]#

Whether Trainer.fit has trained this model.

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

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.

update_weights(flat_weights_dict)[source]#

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[source]#

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.