Add --no_balance flag to not balance datasets
#287
Conversation
| @@ -65,6 +65,9 @@ class Extract(Serializable): | |||
| binarize: bool = False | |||
| """Whether to binarize the dataset labels for multi-class datasets.""" | |||
|
|
|||
| no_balance: bool = False | |||
There was a problem hiding this comment.
Why not just make it
balance: bool = True ?
There was a problem hiding this comment.
That would also avoid having that:
balance=not cfg.no_balance
There was a problem hiding this comment.
Because it would be unclear how to use the flag to disable balancing from the CLA. --balance False or something is weirder than --no_balance
There was a problem hiding this comment.
--balance False does not seem weirder than --no_balance True to me.
But okay, it's fine for me
There was a problem hiding this comment.
Yeah I think I agree with you now
| @@ -212,12 +212,11 @@ def inlp( | |||
| p = y.float().mean() | |||
| H = -p * torch.log(p) - (1 - p) * torch.log(1 - p) | |||
|
|
|||
| if max_iter is not None: | |||
| d = min(d, max_iter) | |||
| max_iter = max_iter or d | |||
There was a problem hiding this comment.
That's just some refactoring which has nothing to do with the balancing I guesS?
There was a problem hiding this comment.
right, I also added a max_iter flag and this was a necessary refactoring
| @@ -6,7 +6,7 @@ | |||
|
|
|||
|
|
|||
| def train_supervised( | |||
| data: dict[str, tuple], device: str, mode: str | |||
| data: dict[str, tuple], device: str, mode: str, max_inlp_iter: int | None = None | |||
There was a problem hiding this comment.
that's a new feature not related to the balancing either, right?
No description provided.