Module ml4opf.models.basic_nn.basic_nn

Classes

class BasicNeuralNet (config: dict,
problem: OPFProblem)

Browse git

A basic feed-forward neural network.

Args

config : dict

Dictionary containing the model configuration.

optimizer (str): Optimizer. Supported: "adam", "adamw", "sgd".

loss (str): Loss function. Supported: "mse", "l1".

hidden_sizes (list[int]): List of hidden layer sizes.

activation (str): Activation function. Supported: "relu", "tanh", "sigmoid".

boundrepair (str): Bound clipping method. Supported: "none", "relu", "clamp", "sigmoid".

learning_rate (float): Learning rate.

problem : OPFProblem

The OPFProblem object.

Ancestors

• OPFModel
• abc.ABC

Subclasses

• ACBasicNeuralNet
• DCBasicNeuralNet
• EDBasicNeuralNet
• SOCBasicNeuralNet
• LDFNeuralNet
• PCANeuralNet
• PenaltyNeuralNet

Instance variables

prop model_cls

Browse git

The LightningModule class to use for training. Must be a subclass of BasicNN.

Methods

def make_dataset(self, seed: int = 42, dl_kwargs: dict | None = None, **kwargs)

Browse git

def make_trainer(self, force_new_trainer=False, **kwargs)

Browse git

def make_training_model(self, force_new_model=False)

Browse git

def train(self,
force_new_model: bool = False,
trainer_kwargs: dict | None = None,
dataset_kwargs: dict | None = None,
fit_kwargs: dict | None = None,
compile_kwargs: dict | None = None)

Browse git

Inherited members

• OPFModel:
  • evaluate_model
  • load_from_checkpoint
  • predict
  • save_checkpoint