Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

COMMON输入自己的数据集 #9

Open
bullshit123123 opened this issue Jul 25, 2023 · 1 comment
Open

COMMON输入自己的数据集 #9

bullshit123123 opened this issue Jul 25, 2023 · 1 comment

Comments

@bullshit123123
Copy link

您好!
我对您的工作非常感兴趣,对于COMMON这篇论文,有几个问题想请教您:
1. 请问我如何输入自己的数据来进行训练以及测试呢?
2. 生成图的代码可以单独摘出来用于生成图吗?

    非常期待您的回复。
@Lin-Yijie
Copy link
Owner

我们的算法中图通过三角剖分构建的,详见

A1, G1, H1, e1 = build_graphs(P1, n1, stg=cfg.GRAPH.SRC_GRAPH_CONSTRUCT, sym=cfg.GRAPH.SYM_ADJACENCY)

这里包含了三角剖分、全联通和阈值图的构建,你可以通过这个函数构建自己的图。

def build_graphs(P_np: np.ndarray, n: int, n_pad: int=None, edge_pad: int=None, stg: str='fc', sym: bool=True,

要使用自己数据训练的话,可以修改train_eval.py里的dataloader。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants