skye95git

> Hi @skye95git, > > I do not have this problem. I guess it is related to your CUDA installation. You may find a similar issue [here](https://github.com/pyg-team/pytorch_geometric/issues/2040). Thanks for your...

> > > Hi @skye95git, > > > I do not have this problem. I guess it is related to your CUDA installation. You may find a similar issue [here](https://github.com/pyg-team/pytorch_geometric/issues/2040)....

> Thanks for the code. Good job. I train graphormer_slim in zinc dataset by bash examples/property_prediction/zinc.sh. Then I try to evalute it by: > > ``` > python graphormer/evaluate/evaluate.py \...

@dongZheX Did you download the data set in advance?

> yes, I tested with torch-geometric 2.0.3 , pytorch 1.10.1, cuda 11.3, nvidia 3090, ubuntu 18.04 python3.9, is ok !!! Why did you change the version? Is it because install.sh...

> Thanks to propose these questions; First, the variability is attention variability, and we think the high value is content-dependent and the low is content-independent. Second, Our input is the...

If input is the pruned AST and code snippet, what are the outputs of models in Syntax Tree Induction? The output is is there an edge between the two nodes,...

> Actually, the purned AST strcuture is the gold standard, and we use the method(in our paper) to induce a binary tree，and compute the similarity between the two trees. Thanks...

Thanks. There are two final questions： 1. So, the attention variability is calculated according to Formula 5, right? If the calculated value is high, it is considered content-dependent head, otherwise,...

> > Thanks for your great work! I have a few questions: > > > > 1. Is the Implementations part model reimplemented by yourselves, or is it the official...