pygcn torch.spmm

Sep 24 '18 09:09 zhuchangjiang

what does this mean?

Sep 24 '18 10:09 zhuchangjiang

Sparse matrix multiplication

On Mon 24. Sep 2018 at 11:12 changjiang.zhu [email protected] wrote:

what does this mean?

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/tkipf/pygcn/issues/19#issuecomment-423929073, or mute the thread https://github.com/notifications/unsubscribe-auth/AHAcYOikqTu-yGmoQqFdfsm3xDQsJzhOks5ueLAMgaJpZM4W2W9g .

Sep 24 '18 10:09 tkipf

It does not work in Pytorch 0.4.1. This function only supports the torch.tensor but not Variable.

Oct 28 '18 04:10 Tanyjiang

Can you try PyTorch 0.5?

Oct 28 '18 18:10 tkipf

I tried a new defined layer for torch.spmm(). It works. Thanks

Oct 29 '18 01:10 Tanyjiang

As a note, torch.spmm may move to torch.sparse.spmm. The API states it is experimental at the moment.

May 28 '19 19:05 jgbradley1

I tried a new defined layer for torch.spmm(). It works. Thanks @Tanyjiang Hey! How do you define the 'spmm' layer? Thanks !

Jun 02 '19 12:06 InstantWindy

In PyTorch 1.8, torch.spmm is deprecated. Unify matrix multiplications operations Deprecate spmm and dsmm functions TORCH.SPARSE 1.8

As a note, torch.spmm may move to torch.sparse.spmm. The API states it is experimental at the moment.

Apr 06 '21 07:04 kprojiang

Could anyone provide a substitution for the deprecated torch.spmm?

Apr 16 '21 17:04 Cogito2012

torch.mm should work, as torch.spmm was just an alias for it, as mentioned in https://github.com/pytorch/pytorch/issues/46164.

Mar 18 '23 06:03 salcc