search

microsoft / Graphormer

Graphormer is a general-purpose deep learning backbone for molecular modeling.
MIT License
2.08k stars 334 forks source link

Using the code for the new dataset that we made. #37

Closed gunahn closed 2 years ago

gunahn commented 2 years ago

I am trying to use a Graphormer on brain intelligence regression problems. So, we are using brain connectivity as an input graph, and we are trying to solve the graph regression problem.

And we set the whole edge and node features as an integer.

We are facing these errors below. expected tensor for argument #1 'indices' to have scalar type long but got torch.FloatTensor instead

So I tried to change the code in model.py (line 162 originally) in a diverse way. image

However, after I changed X.type to the torch.cuda.LongTensor, I am still facing another error related to Cuda.

image image

Can you help me with how to solve the problem?

Thank You

zhengsx commented 2 years ago

Woud you provide more info about your error expected tensor for argument #1 'indices' to have scalar type long but got torch.FloatTensor instead , e.g. the complete error message, the code, and the environment you used?

zhengsx commented 2 years ago

Close this issue due to inactive. Feel free to raise a new one or reopen this one for any further question.