Shuyue Jia (Bruce)
Shuyue Jia (Bruce)
> @xialeiliu 你好请问一下 解压密码是什么？ livedatabase2005
> > Dear Wei, > > Thanks a lot for your excellent summary! It helps a lot in the field. > > Wei, I can see that most SOTA works...
Philips不算是互联网企业吗？Philips也有在做CV和NLP呀，而且在医疗领域CV做的蛮多的哈
How about the labels w.r.t. the regression problem? @Diego999 @tibe97 @AdrianBZG @pbloem @sh0416
> I switched the dataset to citeseer, and trained for 100 epochs, the 99th epoch training log is: > Epoch: 0099 loss_train: 0.9922 acc_train: 0.7000 loss_val: 1.0769 acc_val: 0.7100 time:...
Is there any way to decrease memory usage?
> Is there any solution? I think the solution is to use another effective and efficient graph convolution.
> The memory usage is just too high to use batch training. The input with shape `batch_size × node × in_features` would be expanded to shape `batch_size × node ×...
> The memory usage is just too high to use batch training. The input with shape `batch_size × node × in_features` would be expanded to shape `batch_size × node ×...
@Diego999 @HowardZorn @pbloem @sh0416