search

PacktPublishing / Hands-On-Graph-Neural-Networks-Using-Python

Hands-On Graph Neural Networks Using Python, published by Packt
MIT License
663 stars 181 forks source link

Don't apply log_softmax since CrossEntropyLoss expects logits #4

Closed balvisio closed 1 year ago

balvisio commented 1 year ago

Hello @mlabonne , Thanks for the quick reply. I found another minor issue. According to the Pytorch documentation CrossEntropyLoss expects the logits so the forward() method shouldn't apply log_softmax().

Thanks!

balvisio commented 1 year ago

Hi @mlabonne : I just added another small fix in a new commit. I noticed that in the fit() function when using the NeighborLoader the total_loss was being divided by len(loader.dataset) which in the case of the NeighborLoader returns the total number of nodes since it is an instance of a NodeLoader. IIUC we really want to divide by the total number of graphs so it is more appropriate to divide by len(loader.data). (Dividing by len(loader.dataset) is appropriate when a DataLoader was used)

Thanks!

mlabonne commented 1 year ago

Sorry about the delay. Thank you for your very valid comments, I'm merging your commits. Have a great day!