[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"
How about refactoring some code using torch sparse++? I saw that their paper referenced your work, and it seems like a great library for handling sparse tensors
@xubin04 That's a good idea but currently I don't have time for this. If you're interested you can give it a try and considering submitting a PR to our codebase :D.
How about refactoring some code using torch sparse++? I saw that their paper referenced your work, and it seems like a great library for handling sparse tensors