You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I'm currently trying to apply a different scalar to the loss of each element in a batch , but SumAndDifferenceSTFTLoss doesn't have the option to return element-wise losses (in most loss functions this is reduction="none"). Is this feasible to add?
The text was updated successfully, but these errors were encountered:
After taking a look into this I see why it wasn't implemented in the first place. Handling operation for reduction = "none" is non-trivial for any loss that has multiple sub-components. We have been thinking for a while to provide a different interface for computing losses that would involve a Transform and a Distance which would make this behavior more clear. We might have to wait for this interface in order to support this feature. However, this use-case provides more reasoning to work on this.
I will keep this issue open for now, but follow #16 if you are interested.
I'm currently trying to apply a different scalar to the loss of each element in a batch , but
SumAndDifferenceSTFTLoss
doesn't have the option to return element-wise losses (in most loss functions this isreduction="none"
). Is this feasible to add?The text was updated successfully, but these errors were encountered: