zjukg / adamf-mat Goto Github PK

Hello, I have some questions to ask about the raw data used in this paper:

1. Did you use the embeddings which is provided beforehand, or generate it from the raw data?
2. If you use raw data, where did you retrieve it, and did you check it before generating embeddings, because I checked and realized that the number of entities in the dataset you referenced and the statistics is not similar.
3. I tried to scrap data from the links you provided in /benchmarks but MKG-W data is broken, meanwhile MKG-Y doesn't consist links to scrap. Can you check it out?

Thanks! Hope to receive your answer!

在尝试运行代码时，发现电脑报错是不是有用的win32程序，报错的文件是base.so文件，我的电脑是win64。通过网上查询得知base.so文件是linux系统运行文件，尝试使用32位python去运行，结果出现Microsoft Visual C++ Redistributable is not installed报错。我想知道您运行代码是在linux系统运行吗，使用的是32位系统吗，base.so文件有没有win可替代的文件

When I was training, I made the following errors：
Namespace(adv_num=1, adv_temp=2.0, batch_size=1024, con_temp=0, dataset='FB15K', dim=250, epoch=1000, img_dim=4096, lamda=0, learning_rate=0.0001, lrg=0.0001, margin=12.0, missing_rate=0.8, mu=0.0, neg_num=128, postfix='', save='./checkpoint/DB15K-1024-250-128-12-1e-4-1000', seed=42, visual='random')
Input Files Path : ./benchmarks/FB15K/
The toolkit is importing datasets.
Segmentation fault (core dumped)

I see MMRNS only provide the *.h5 embedding files, would you mind provide the *.pth you used in the paper. Thx.