When using batches on a small dataset, there is a chance that a molecule size that is present in the data is not present in the batch. This is not correctly handled in the logic and throws an error.
I've fixed this on my end, let me know if I should make a branch so I can create a pull request.
When using batches on a small dataset, there is a chance that a molecule size that is present in the data is not present in the batch. This is not correctly handled in the logic and throws an error.
I've fixed this on my end, let me know if I should make a branch so I can create a pull request.