huizhang
huizhang
文中没有提到loss function和如何训练,具体是怎么训练的呢？
How to output the probability that each subgraph is 0 or 1, such as (P(g=0), P(g=1)), if I input 50 subgraphs, how can I output the probability label of 50*2...
The output prediction result of each subgraph should be a 2-dimensional tuple. I want to get the normalized probability. If take exponential of the logits to get the predicted probabilities...
Ok.Thanks.
> https://github.com/muhanzhang/pytorch_DGCNN/blob/50f504131ca66382f3f078ae98e59aa3ae35b795/main.py#L154 > > logits > > You can use loop_dataset(): > > https://github.com/muhanzhang/pytorch_DGCNN/blob/50f504131ca66382f3f078ae98e59aa3ae35b795/main.py#L223 > > Loss, accuracy and logits are generated inside the loop_dataset() function. Where are the predicted...
OK.Thank you!
If I input 100 graph objects to the model, the output feature is 100*32. Does 1*32 here represent the embed of a graph object?
I got it.Thank you very much！
hi，data/dreamdata/data4_pmatrix_0.8.npy，How this noise frame is calculated?The links I calculated directly from gene expression data 4 far exceeded 54224 links