saealib.TorchSurrogate

class saealib.TorchSurrogate(model, optimizer_cls=None, optimizer_kwargs=None, loss_fn=None, epochs=100)

ベースクラス: RegressionSurrogate

Surrogate adapter for PyTorch nn.Module models.

Wraps any torch.nn.Module that maps (n_samples, n_features) to (n_samples, n_obj). The model is trained from scratch on each fit call by resetting to the weights captured at construction time, so this adapter is safe to use with LocalSurrogateManager (which re-fits per candidate).

パラメータ:

• model (torch.nn.Module) -- Neural network model. Its output shape must be (n_samples, n_obj).

• optimizer_cls (type or None) -- Optimizer class (e.g. torch.optim.Adam). Defaults to torch.optim.Adam.

• optimizer_kwargs (dict or None) -- Keyword arguments forwarded to the optimizer constructor. Defaults to {}.

• loss_fn (callable or None) -- Loss function. Defaults to torch.nn.MSELoss().

• epochs (int) -- Number of training epochs per fit call. Default: 100.

例外:

ImportError -- If PyTorch is not installed.

Methods

__init__
contract	Return the surrogate model contract.
fit	Fit the surrogate model.
post_fit	Post-fit lifecycle hook; override to inject custom processing.
predict	Predict using the surrogate model.
with_post_fit	Return a copy of this surrogate with fn appended to the post-fit hook.

Method Details

TorchSurrogate.__init__(model, optimizer_cls=None, optimizer_kwargs=None, loss_fn=None, epochs=100)

パラメータ:

• model (torch.nn.Module)

• optimizer_cls (type | None)

• optimizer_kwargs (dict | None)

• loss_fn (Callable[..., Any] | None)

• epochs (int)

戻り値の型:

None

TorchSurrogate.contract()

Return the surrogate model contract.

戻り値の型:

ComponentContract

TorchSurrogate.fit(train_x, train_y)

Fit the surrogate model.

Resets model weights to their initial values before training.

パラメータ:

• train_x (np.ndarray) -- Training input data. shape: (n_samples, n_features)

• train_y (np.ndarray) -- Training output data. shape: (n_samples, n_obj) or (n_samples,).

戻り値の型:

None

TorchSurrogate.post_fit(train_x, train_y, ctx=None)

Post-fit lifecycle hook; override to inject custom processing.

パラメータ:

• train_x (np.ndarray) -- Training input data used for this fit. shape: (n_samples, n_features)

• train_y (np.ndarray) -- Training output data used for this fit. shape: (n_samples, n_obj)

• ctx (OptimizationState or None, optional) -- Current optimization context.

戻り値の型:

None

TorchSurrogate.predict(test_x)

Predict using the surrogate model.

パラメータ:

test_x (np.ndarray) -- Input data. shape: (n_samples, n_features) or (n_features,)

戻り値:

prediction.value shape: (n_samples, n_obj) prediction.std is None

戻り値の型:

SurrogatePrediction

TorchSurrogate.with_post_fit(fn)

Return a copy of this surrogate with fn appended to the post-fit hook.

パラメータ:

fn (callable) -- fn(train_x, train_y, ctx) -> None

戻り値:

Shallow copy with the hook registered.

戻り値の型:

Surrogate