Karthik Prasad

Hello! Thanks for raising the issue. I'll take a look at get back to you on this.

Hi @SeolhwaLee. Are you using a different sampler that is resulting in an empty batch? If yes, is that intentional?

Hi @SeolhwaLee , The tutorial you linked does not use RandomSampler. When you call `make_private()` and pass your dataloader, Opacus internally switches it with [DPDataLoader](https://github.com/pytorch/opacus/blob/main/opacus/data_loader.py#L70) that uses [Uniform Batch Sampler](https://github.com/pytorch/opacus/blob//opacus/utils/uniform_sampler.py#L22)...

Thanks for flagging @kjam, I'll take a look at this.

Hi @kjam , I took a look at this and can confirm that the tutorial https://opacus.ai/tutorials/building_text_classifier runs correctly. I did not test this with the kaggle dataset that your notebook...

@kjam , your `batch` is a dict, so t in `for t in batch` will iterate over `batch`'s keys, which are strings and cannot be moved to cuda. I suppose...

Closing the issue since the main issue has been resolved.

Thanks for flagging @albertyusun! I think this issue is generic enough to be filed on pytorch repo directly. WDYT @samdow , @ffuuugor ?

Thanks @FrancescoPinto , I'll take a look at this.

The reason for this incompatibility is due to presence of `nn.Parameter()` in `ConvNext`'s block, which is not present in , say, a `ResNet`'s block. This, therefore, requires explicit handling via...