Matthias Fey

I think we can do this. IMO, this should be quite straightforward to implement, since we just need to write the distances into an additional output vector. I would very...

Those are the CPU/CUDA (`csr/cpu`/`csr/cuda`) kernels injected into PyTorch by `torch_cluster/__init__`.

Yes, that's tricky indeed. I prefer to use a vector of `N-1`, but what is the best may heavily depend on the use-case.

You can track the progress here: https://github.com/rusty1s/pytorch_cluster/pull/85

Sounds like a great thing to add. Are you interested in contributing this feature?

Yes, we will add support for this in the next upcoming release. Please stay tuned :)

Thank you @pbielak, will have a look ASAP.

Thanks for reporting. How does the `try`/`except` block resolves this issue? Do you make use of a custom dataset?

The following code works fine for me, super weird :( ```python import pickle from torch_cluster import fps with open('fps_err_0.pkl', 'rb') as f: data = pickle.load(f) x, pos, batch = data...

Thanks for sharing. I will do some further digging on my end as well.