About different results running the same code
zhandand opened this issue · 2 comments
zhandand commented
Though I have fix the seed, the results after running the same code are different. Do u have any ideas about that?
` random.seed(0)
np.random.seed(0)
torch.manual_seed(0)
torch.cuda.manual_seed_all(0)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False`
SXKDZ commented
Thanks for your interests. Your referred information is correct. That has something to do with PyG's side. You need to convert the sparse adjacency matrix to adj_t
type. Please refer to their tutorial on the randomness in experiments.