Add Citing note.

README.md

@@ -9,9 +9,14 @@ settings.
 
 Decagon-PyTorch is a PyTorch reimplementation of the algorithm.
 
+## Citing
+
+If you use this code in your research please cite this repository as:
+
+Adaszewski S. (2020) https://code.adared.ch/sadaszewski/decagon-pytorch
+
 ## References
 
 1. Zitnik, M., Agrawal, M., & Leskovec, J. (2018).
 [Modeling polypharmacy side effects with graph convolutional networks](https://academic.oup.com/bioinformatics/article/34/13/i457/5045770)
 Bioinformatics, 34(13), i457-i466.
-

experiments/decagon_run/decagon_run.py

@@ -109,7 +109,7 @@ def _wrap(obj, method_name):
 
 
 def main():
-    dev = torch.device('cuda:0')
+    dev = torch.device('cpu')
     data = load_data(dev)
     prep_d = prepare_training(data, TrainValTest(.8, .1, .1))
     _wrap(Model, 'build')