Predictors

DNN Ensemble

class archai.discrete_search.predictors.dnn_ensemble.PredictiveDNNEnsemble(num_ensemble_members: int | None = 5, num_layers: int | None = 5, width: int | None = 64, lr: float | None = 0.0001, num_tr_steps: int | None = 2000, replace_nan_value: float = -1.0, device: str | None = 'cuda')

Deep Neural Network Ensemble predictor.

Predicts the outcome of a set of expensive objectives using an ensemble of MLP models.

to_cuda() → None

Moves the predictor to CUDA.

to_cpu() → None

Moves the predictor to CPU.

fit(X: ndarray, y: ndarray) → None

Fit a predictor model using an array of encoded architectures (N, #features) and a multi-dimensional array of targets (N, #targets).

Parameters:

• encoded_archs – (N, #features) numpy array.

• y – (N, #targets) numpy array.

predict(X: ndarray) → MeanVar

Predict the performance of an array of architectures encoded by by a subclass implementation of BayesOptSearchSpaceBase.encode().

Parameters:

encoded_archs – Array of encoded architectures.

Returns:

Named tuple with mean (N, #targets) and var (N, #targets) arrays.

class archai.discrete_search.predictors.dnn_ensemble.FFEnsembleMember(num_objectives: int | None = 1, input_feat_len: int | None = 128, num_layers: int | None = 10, width: int | None = 20)

Feedforward ensemble member.

forward(x: Tensor) → Tensor

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

training: bool