Open YJPQQ opened 2 years ago
According to the MAML paper,in line 268 of the file 'run.py', meta_loss should not be divided by task_num, right?
I referred to MAML-Pytorch and pytorch-maml, where meta_loss is divided by task_num. I think it can normalize the loss.
According to the MAML paper,in line 268 of the file 'run.py', meta_loss should not be divided by task_num, right?