Bug
The bug happens if less than 6 features is used in the FourierEncoder class. The script will terminate with the following error
RuntimeError: It looks like your LightningModule has parameters that were not used in producing the loss returned by training_step. If this is intentional, you must enable the detection of unused parameters in DDP, either by setting the string value strategy='ddp_find_unused_parameters_true' or by setting the flag in the strategy with strategy=DDPStrategy(find_unused_parameters=True)
This happens because self.aux_emb is initialized whether or not it is used.
Bug The bug happens if less than 6 features is used in the FourierEncoder class. The script will terminate with the following error
This happens because self.aux_emb is initialized whether or not it is used.