Hi,
In model_step, we have se3_vf_loss += auxiliary_loss. Yet in training_step, we also have `train_loss = (
total_losses[self._exp_cfg.training.loss]
total_losses['auxiliary_loss']
) The default training loss isse3_vf_loss` so in this case, auxiliary loss is being counted twice in the loss. Is this expected or a bug?
Hi, In
model_step
, we havese3_vf_loss += auxiliary_loss
. Yet intraining_step
, we also have `train_loss = ( total_losses[self._exp_cfg.training.loss]The default training loss is
se3_vf_loss` so in this case, auxiliary loss is being counted twice in the loss. Is this expected or a bug?Thanks!