RNN module weights are not part of single contiguous chunk of memory，对我有效可以试一试

I met the same problem and solved it by adding

self.rnn.flatten_parameters()

into the

def forward(self, x)

at the position before calling

rnn_output, _ = self.rnn(x, h)

By doing so, the error never showed up.
如果想看如何解决详情查看这个链接

我在rnn_out 前加了个图片所高亮的代码，解决了我的问题。