Cannot use GPU when output.shape[1] * nnz(a) > 2^31 about keras-gcn HOT 10 OPEN

from keras-gcn.

I meet this problem too ！

from keras-gcn.

hello, do you solve it? can you share your method? thanks

from keras-gcn.

No

from keras-gcn.

Is there any solution on this issue?

from keras-gcn.

@innekemayachita Have you found anything maybe?

from keras-gcn.

You can cast the sparse matrix to dense matrix and use tf.matmul

from keras-gcn.

Same problem here.

from keras-gcn.

You can cast the sparse matrix to dense matrix and use tf.matmul

But if we have a large matrix with most of zero, we would like to use sparse matrix, so shouldn't cast to dense matrix

from keras-gcn.

I had this problem on tensorflow 2.4.1, it went away when I upgraded to 2.5 + cuda lib v11; I don't know if the trouble was with the tensorflow version, cuda, or both.

from keras-gcn.