search

lukecavabarrett / pna

Implementation of Principal Neighbourhood Aggregation for Graph Neural Networks in PyTorch, DGL and PyTorch Geometric
https://arxiv.org/abs/2004.05718
MIT License
338 stars 55 forks source link

Bug in device check #8

Closed zhanqiuzhang closed 3 years ago

zhanqiuzhang commented 3 years ago

The type of device is either torch.device("cuda") or torch.device("cpu"). Thus, device == 'cuda' will always be False and torch.cuda.manual_seed(params['seed']) will not work.

gcorso commented 3 years ago

Thank you very much for noticing, I should have fixed it now. Fortunately, we did not use manual seeds in our experiments.