Zeyuan Wang

Results 2 issues of Zeyuan Wang

这里的[dfs](https://github.com/linrongbin16/way-to-algorithm/blob/e666edfb000b3eaef8cc1413f71b035ec4141718/src/GraphTheory/Traverse/EulerCycle.cpp#L26)函数只是做了一个简单的深度优先遍历节点,path并不是最终的回路,比如下面这个测试样例的path结果就不正确: > { > { > {0, 1, 1, 0, 0}, > {1, 0, 1, 1, 1}, > {1, 1, 0, 0, 0}, > {0, 1, 0, 0, 1}, >...

作者您好,我和朋友在运行这份代码的时候发现这样一个问题: query的输入顺序是和support的顺序固定一致的,此时训练后的模型在验证集上准确率能有85.684%,比较高。然而在把query的顺序打乱的情况下训练模型,只能在验证集上得到77.042%的准确率。公认的是,query的顺序应该被打乱。我们认为是您的图神经网络出现了过拟合,学习到了query的固定顺序。您能对此作出解释吗?感谢。(上述准确率均是在一块2080ti GPU上训练得到的结果,由于显存的原因,我将train_batch_size和test_batch_size改小到了32和16) Hello author, friends and I found this problem when running this code: The input order of query is consistent with the order of support. At this time,...