benedekrozemberczki / pytorch_geometric_temporal

PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)
MIT License
2.58k stars 367 forks source link

Return type annotation of GCLSTM and GConvLSTM forward changed to Tuple #248

Open apfelsinecode opened 10 months ago

apfelsinecode commented 10 months ago

forward of GConvLSTM and GCLSTM return two FloatTensors, H and C. This PR reflects that in the signature, by changing the return type from torch.FloatTensor to Tuple[torch.FloatTensor, torch.FloatTensor].