Memory error !!!

[abhigoku10]

@Diego999 i am getting the following error all_combinations_matrix = torch.cat([Wh_repeated_in_chunks, Wh_repeated_alternating], dim=1) RuntimeError: CUDA out of memory. Tried to allocate 896.00 MiB (GPU 0; 6.00 GiB total capacity; 4.12 GiB already allocated; 162.50 MiB free; 4.48 GiB reserved in total by PyTorch) any insights on these

THanks in advance

[Scofield666]

I met with the error as well, have you solved this problem yet?

[Wings236]

Maybe, your memory is not enough to be used. Because it use 7GB+ memory to run this dataset.

[SuperBruceJia]

Is there any way to decrease memory usage?

[lbq8942]

why a graph 2708 nodes need so much memory?

[Cinderella1001]

I also met this problem, is there any solution?

[jiaojiaoguan]

Is there any solution?

[SuperBruceJia]

Is there any solution?

I think the solution is to use another effective and efficient graph convolution.