Prasanna Sattigeri

> I can pick this up. If you can assign this to me, that would be perfect. Thanks assigned it to you.

Thanks @FeSens. This is helpful and can be temporary fix. Looks like we should support the use of dataloader in the `fit` method for `BNNRegression` similar to `BNNClassification`. I have...

@jirin1a do you have thoughts on this?

@giandos200 @nrkarthikeyan If I remember correctly, we were not seeing big differences with these enhancements across datasets. So we decided to keep the basic version of approach. @giandos200 Please free...

> @pronics2004 @nrkarthikeyan i'm trying to pass the continuous integration test for the Pull Request but did not pass the test Continuous Integration / build-py (3.6/3.7/3.8) since the adversary test...

Could you please provide a code snippet of the issues or some more details about your use case. Are you creating multiple instances of the AdversarialDebiasing in the same session?...

Yes, this is a valid point. `fit()` here was designed to be called once on the whole dataset. Changing the `scope_name` for each instance of `AdversarialDebiasing ` should fix this....

Thanks @janfelixklein. We will follow up on this issue. Meanwhile, if you have a working fix, please feel free to submit a PR. FYI: @SoumyaTGhosh

Hi @devdrian This will be quite useful. You are welcome to create a merge request! [](url) Please refer to [CONTRIBUTING.md](https://github.com/IBM/UQ360/blob/main/CONTRIBUTING.md) as you create the PR.