vmiller987

Here's my fix :) https://github.com/MIC-DKFZ/batchgeneratorsv2/pull/14

> [@vmiller987](https://github.com/vmiller987), did you solve your issue? Oof, no I did not. I actually closed the wrong issue. I was rushing last week. I haven't had time to dig into...

> Hi [@vmiller987](https://github.com/vmiller987), > > I think the issue arises as in the `resample_and_seg` neither `chunks_seg` nor `blocks_seg` are set, which in `blosc2.asarray` leads to the observed error. There needs...

@ykirchhoff I have not been able to replicate this problem. We've done major refactors on how we store and use our datasets along with discovering some hardware issues that we've...

I'm not an expert, but I think I can answer part of your question. Hopefully this helps you. Fold "all" uses ALL the training data as validation data. This usually...

That's good you don't have label imbalance. I have too many datasets with label imbalances... So for cross validation, the developers setup a nifty function that will find your best...

I haven't had time to test older torch versions, but I've had this feeling since upgrading for the same reasons. I'll try to test as well, as I have been...

> Experiment will run for a while still, but if we see something then this might be the culprit: [pytorch/pytorch#163539](https://github.com/pytorch/pytorch/issues/163539) This is certainly interesting. Is there anything I can do...

I have some insanely large 3D images (10-60Gb) in size. I run into the same issue with these on an RTX Pro 6000 with 96GB of VRAM. I've just assumed...

This issue talks about it slightly: https://github.com/MIC-DKFZ/nnUNet/issues/2234#issue-2320469317 The paper also explains it: "For all other networks we interpret the samples in the batch as a pseudo-volume and compute the dice...