FeiGSSS/DySAT_pytorch

error

Opened this issue · 2 comments

zhaohaixiangbobo commented

sometimes it runs this error
image

but sometimes it not

FeiGSSS commented

sometimes it runs this error image

but sometimes it not

It seems like something is wrong with the data input. I'd suggest you print the outputs of the model's prediction and check whether the shapes and the values are valid.

If this turns out to be caused by a bug, welcome to submit a PR.

zhaohaixiangbobo commented

sometimes it runs this error image
but sometimes it not

It seems like something is wrong with the data input. I'd suggest you print the outputs of the model's prediction and check whether the shapes and the values are valid.

If this turns out to be caused by a bug, welcome to submit a PR.

一个没想到的bug
image
image
nn.Parameter(torch.Tensor(1, n_heads, self.out_dim))生成的时候就是nan，属实第一次见

建议还是用
self.att_l = nn.Parameter(torch.zeros(1, n_heads, self.out_dim))
self.att_r = nn.Parameter(torch.zeros(1, n_heads, self.out_dim))
或者
randn/rand吧

  • 👍1