Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same

ML4ITS / mtad-gat-pytorch

PyTorch implementation of MTAD-GAT (Multivariate Time-Series Anomaly Detection via Graph Attention Networks) by Zhao et. al (2020, https://arxiv.org/abs/2009.02040).

MIT License

328 stars 76 forks source link

Input type (torch.cuda.FloatTensor) and weight type (torch.FloatTensor) should be the same #23

Closed xiaokai01 closed 1 year ago

srigas commented 1 year ago

This happens when your data are on the GPU (torch.cuda.FloatTensor), but your model is not. You need a model.to(device) line, where device is something like cuda:0.