Open nehSgnaiL opened 2 months ago
Hi,
Thanks for the remarkable work.
I would like to know more about the operations in defined loss. Since the mask has been normalized by mask /= torch.mean(mask), should we use the sum operation torch.sum(loss) rather than the mean operation torch.mean(loss) in returning loss?
mask
mask /= torch.mean(mask)
torch.sum(loss)
torch.mean(loss)
https://github.com/LibCity/Bigscity-LibCity/blob/38ff38353ea71045b69260bb2e6875cb0abf95ad/libcity/model/loss.py#L75-L87
I am not sure what I understand is right due to my limited knowledge. If you could respond, that would be greatly appreciated.
The codes mask /= torch.mean(mask) and return torch.mean(loss) work properly. The outcome appears to be correct, but I find it difficult to read.
return torch.mean(loss)
Hi,
Thanks for the remarkable work.
I would like to know more about the operations in defined loss. Since the
mask
has been normalized bymask /= torch.mean(mask)
, should we use the sum operationtorch.sum(loss)
rather than the mean operationtorch.mean(loss)
in returning loss?https://github.com/LibCity/Bigscity-LibCity/blob/38ff38353ea71045b69260bb2e6875cb0abf95ad/libcity/model/loss.py#L75-L87
I am not sure what I understand is right due to my limited knowledge. If you could respond, that would be greatly appreciated.