CondGen icon indicating copy to clipboard operation
CondGen copied to clipboard

Conditional Structure Generation through Graph Variational Generative Adversarial Nets, NeurIPS 2019.

Results 5 CondGen issues
Sort by recently updated
recently updated
newest added

--------------------------------------------------------------------------- AssertionError Traceback (most recent call last) in () 26 e = int(np.sum(train_adj_mats[i])) // 2 27 ---> 28 c_adj = topk_adj(F.sigmoid(rec_adj), e * 2) 29 c_noise = topk_adj(F.sigmoid(rec_noise), e *...

I have trained a CondGEN model with the default settings in ```options.py```. But I can't make the trained model perform as well as yours scriped in the paper. And I...

Hi! How to generate a graph after training? Could you please add the inference code?

Hello! I'm training the model, and when I uncomment` show_graph(sample_adj, base_adj=base_adj, remove_isolated=True)` in order to check output I got: `Values less than or equal to 0 in data. Throwing out...