liangyx

run python make_dataset.py get some error

3

 hello, i run python3 make_dataset.py --target cuda --logs dataset/measure_records/k80/*.json and get this error. can you help me, best wishes

spspmm lead to error: PyTorch CUDA error: an illegal memory access was encountered.

27

Hi, I'm having the same problem with #174. I have two large adjacency matrices, the details are as follows adj_l SparseTensor(row=tensor([ 0, 0, 0, ..., 736388, 736388, 736388], device='cuda:2'), col=tensor([...

The code's learning rate hyperparameters seems inconsistent with the paper.

3

Hello, the learning rate of cora, citeseer, and pubmed is 0.02 in the paper. But it seems to be 0.2 in the implementation. Which one is correct? In addition, can...

The figure shows the storage overhead in the last row. Can you explain how to calculate it with a specific example?

For NARS_GAMLP+RLU+SCR command: python main.py --use-rlu --method JK_GAMLP_RLU --stages 250 200 200 200 200 200 200 --train-num-epochs 0 0 0 0 0 0 0 --threshold 0.4 --input-drop 0.1 --att-drop 0...

Hello, I tested the gpma_bfs, and very interested in the field of multi-GPU graphics processing, I wonder if you can provide multi-gpu version of the code for reference. Anyway,thanks for...

hello，i run the step as you write. but get some mistakes.would you please offer some helpfor me?

3

node_num: 1632803, edge_num: 30622564 Graph file is loaded. terminate called after throwing an instance of 'thrust::system::system_error' what(): device free failed: unknown error Aborted (core dumped)