About keep_ind

[hetang-wang]

Thank you so much for sharing the work!When I try to run the code on ABIDE-I,an error occured:

lg-gnn/layer.py：180：Runtime Warning：Mean of empty sLice.
edge_input=(edge_input-edge_input.mean(axis=0) ) /edge_input.std(axis=0)

When I tried to edit the following code change 1.1 to 0.4, it still didn't fix the problem：
util.py : 113 : keep_ind = np.where(aff_score > 1.1)[0]

Looking forward to your reply, thank you！

[cnuzh]

Thank you so much for sharing the work!When I try to run the code on ABIDE-I,an error occured:

lg-gnn/layer.py：180：Runtime Warning：Mean of empty sLice. edge_input=(edge_input-edge_input.mean(axis=0) ) /edge_input.std(axis=0)

When I tried to edit the following code change 1.1 to 0.4, it still didn't fix the problem： util.py : 113 : keep_ind = np.where(aff_score > 1.1)[0]

Looking forward to your reply, thank you！

The error "Mean of empty sLice." appears to be a problem with your input data, you can check your data again.

[cnuzh]

兄弟，你知道怎么下载本文的数据集吗，求问下载abide的时候python指令的derivative是什么

@natlank The link to download the data has been given in the original article, and the corresponding websites have detailed instructions.

[Mihkelwork]

非常感谢您分享工作！当我尝试在 ABIDE-I 上运行代码时，发生错误：

lg-gnn/layer.py：180：运行时警告：空虱子的平均值。 edge_input=（edge_input-edge_input.mean（轴=0） ） /edge_input.std（轴=0）

当我尝试将以下代码更改为 1.1 到 0.4 时，它仍然没有解决问题： util.py ： 113 ： keep_ind = np.where（aff_score > 1.1）[0]

期待您的回复，谢谢！

你好，我也遇到了相同的问题，请问是如何解决的问题

[sws827767542]

您好,请问十折交叉验证的每一折的最终的精度为什么和其他折相差较大?