simsiam

SimSIAM(model, projection_mlp, prediction_mlp, criterion, classifier=None, optimizer=None, lr_scheduler=None, lr_scheduler_interval='epoch')

Bases: SSLModule

SimSIAM model.

Parameters:

• model (Module) –

  Feature extractor as pytorch torch.nn.Module

• projection_mlp (Module) –

  optional projection head as pytorch torch.nn.Module

• prediction_mlp (Module) –

  optional predicition head as pytorch torch.nn.Module

• criterion (Module) –

  loss to be applied.

• classifier (ClassifierMixin | None, default: None ) –

  Standard sklearn classifier.

• optimizer (Optimizer | None, default: None ) –

  optimizer of the training. If None a default Adam is used.

• lr_scheduler (object | None, default: None ) –

  lr scheduler. If None a default ReduceLROnPlateau is used.

• lr_scheduler_interval (str | None, default: 'epoch' ) –

  interval at which the lr scheduler is updated.

Source code in quadra/modules/ssl/simsiam.py

def __init__(
    self,
    model: torch.nn.Module,
    projection_mlp: torch.nn.Module,
    prediction_mlp: torch.nn.Module,
    criterion: torch.nn.Module,
    classifier: sklearn.base.ClassifierMixin | None = None,
    optimizer: torch.optim.Optimizer | None = None,
    lr_scheduler: object | None = None,
    lr_scheduler_interval: str | None = "epoch",
):
    super().__init__(
        model,
        criterion,
        classifier,
        optimizer,
        lr_scheduler,
        lr_scheduler_interval,
    )
    # self.save_hyperparameters()
    self.projection_mlp = projection_mlp
    self.prediction_mlp = prediction_mlp