error when train

[Elii-hyy]

When I was training, the following error occurred，and I don't know how to correct it。

Traceback (most recent call last): File "/Users/heyingying/PycharmProjects/PLELog/approaches/PLELog.py", line 255, in loss = plelog.forward(tinst.inputs, tinst.targets) File "/Users/heyingying/PycharmProjects/PLELog/approaches/PLELog.py", line 56, in forward tag_logits = self.model(inputs) File "/Users/heyingying/opt/anaconda3/envs/pytorch/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1194, in _call_impl return forward_call(*input, *kwargs) File "/Users/heyingying/PycharmProjects/PLELog/models/gru.py", line 71, in forward represents = hiddens sent_probs RuntimeError: The size of tensor a (200) must match the size of tensor b (100) at non-singleton dimension 2

[LeonYang95]

Thanks for the comment!

However, it was a size mismatch error when performing the multiplication in attention, I cannot help without the specific setting of yours. Perhaps you should check your configurations first.

Here's a clue that may help: when the bidirectional options are set as True in nn.GRU(), the hidden states will double since it contains information from both directions(i.e., forwards and backwards). So the 2nd dimension of variable hiddens, as shown in this error message, will be doubled. The error message says that a has a size of 200 in dimension 2 while the other one is 100, I think this could be the reason.

If anything goes wrong, please let me know.

[superzeroT]

我在训练的时候出现了如下错误，不知道如何纠正。

回溯（最近一次调用最后）： 文件“/Users/heyingying/PycharmProjects/PLELog/approaches/PLELog.py”，第255行， 损失= plelog.forward（tinst.inputs，tinst.targets） 文件“/Users/heyingying /PycharmProjects/PLELog/approaches/PLELog.py”，第 56 行，前向 tag_logits = self.model(inputs) 文件“/Users/heyingying/opt/anaconda3/envs/pytorch/lib/python3.10/site-packages/ torch/nn/modules/module.py”，第 1194 行，在 _call_impl returnforward_call(*input, *kwargs) 文件“/Users/heyingying/PycharmProjects/PLELog/models/gru.py”，第 71 行，在forward 中 表示=hiddenssent_probs 运行时错误：张量 a (200) 的大小必须与非单一维度 2 处的张量 b (100) 的大小匹配

May I ask if this problem has been solved?I have also encountered the same problem.