Closed jessxphil closed 3 years ago
Thanks for your interest!
experimental
branch (https://github.com/snap-stanford/neural-subgraph-learning-GNN/issues/16#issuecomment-860029505) and the suggested workaround in that thread for a way to train on custom datasets while making use of node features.embs = model.emb_model(batch).detach().cpu().numpy()
. See https://github.com/snap-stanford/neural-subgraph-learning-GNN/blob/4d074cbc0fa9d81defef746302e62b1b9a97791d/subgraph_matching/alignment.py#L54 for an example.Thank you for the clear explanation! I really appreciate your help!
Thank you in advance for your help!
I don't want to use up too much of your time so I'll try to write a few concise questions.
I ran the 'Train' code but the preloaded model didn't update according to the new weights/bias from my personal data. How can I make sure I'm training the model according to my data?
I'm looking to extract the embedded space to use as input features for another model. Just to confirm, is that embedded space stored in the 'pred' variable from the Train.py? [Note: pred = model(emb_as, emb_bs) #Line 131 or pred = pred.argmax(dim=-1) #Line 148]
ALSO There's another embedded space variable from the Analyze_Embedding.pybd. [Note: embs = model.emb_model(batch).detach().cpu().numpy() #Line 79]