In the __init__s of SemanticTransformerTrainer, CoarseTransformerTrainer and FineTransformerTrainer, the attribute self.use_wandb_tracking was only set when the parameter use_wandb_tracking was True. This caused the Trainers to throw an AttributeError upon training when not using WandB.
In the
__init__
s ofSemanticTransformerTrainer
,CoarseTransformerTrainer
andFineTransformerTrainer
, the attributeself.use_wandb_tracking
was only set when the parameteruse_wandb_tracking
wasTrue
. This caused the Trainers to throw anAttributeError
upon training when not using WandB.This is now fixed.