search

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

Fix numerical bug in introduction.rst examples #233

Closed boykovdn closed 1 year ago

boykovdn commented 1 year ago

y_hat is of dimension [N,1] and snapshot.y is of dimension [N]. If subtracted without first removing the trailing dimension of y_hat, then the operation is broadcast to [N,N]. Instead a N-dimensional vector is expected which is then used to compute the MSE.

I've used squeeze() to remove the trailing dimension and computed the training and evaluation.

SimonPop commented 1 year ago

fixes #231

boykovdn commented 1 year ago

Thanks for reviewing! Added another line with the seed and I ran the scores on my machine. Hopefully should be the same if you ran them!