Thomas Kipf
Thomas Kipf
Thanks -- I'll leave this open for now in case someone is interested in a (working) example for a more efficient implementation. I rolled the master branch back to the...
Hi Roman, thanks for reporting this. It is certainly possible to optimize the memory efficiency of the model (e.g. computing higher-order terms from the Chebyshev polynomial on the fly and...
> If i understand well : the less K is, the more filters are localized . AM l wrong ? Yes, exactly. Filters that are polynomials in the adjacency matrix...
See here: https://www.tensorflow.org/guide/using_gpu On Thu 14. Feb 2019 at 16:47 Malika Saksena wrote: > Hi, I was wondering how you assign the tensors to the GPU in the first >...
These are logits -- you can get probability values / normalized scores by passing these through a logistic sigmoid function. On Thu, Jul 4, 2019 at 9:59 AM yjyGo wrote:...
Thanks a lot! I'll try to have a look soon.
I'll leave this open for now, so anyone can patch/merge it locally if they need these updates. I'm unable to test the commit right now, but I would nonetheless recommend...
Sparse matrix multiplication On Mon 24. Sep 2018 at 11:12 changjiang.zhu wrote: > what does this mean? > > — > You are receiving this because you are subscribed to...
Can you try PyTorch 0.5?
Maybe this is helpful: https://github.com/tkipf/gcn/issues/4