Bug: TypeError when lambda_cyc_growth_target=None

[vadori]

When lambda_cyc_growth_target is left as None (its default/optional value), training crashes with:

TypeError: unsupported operand type(s) for *: 'NoneType' and 'int'

This happens at:

weight_cyc = self.calculate_weight(
    self.batches_done,
    self.lambda_cyc_growth_target * len(train_dataloader),
    0, self.lambda_cyc, 1
)

The hyperparameter therefore does not behave as truly optional.