I'm working on a series of data augmentations for text and have implemented their use via the torch.utils.data.DataLoader.collate_fn but jiant appears to be using this function already. Is there a recommended workaround or roadmap item to accommodate custom a collate_fn alongside your own? If not, I'll just work on my own changes and possibly submit as a pull request.
I'm working on a series of data augmentations for text and have implemented their use via the
torch.utils.data.DataLoader.collate_fn
butjiant
appears to be using this function already. Is there a recommended workaround or roadmap item to accommodate custom acollate_fn
alongside your own? If not, I'll just work on my own changes and possibly submit as a pull request.