pytorch初始化RNN权重的方法

RNN的weight和bias封装在parameters中，且需要对weight和bias分开初始化，否则会报如下错误！

Fan in and fan out can not be computed for tensor with fewer than 2 dimensions

在模型定义的__init__函数中进行初始化：

self.rnn = nn.LSTM(input_size=embedding_size, hidden_size=128, num_layers=1, bidirectional=False)
for name, param in self.rnn.named_parameters():
	if name.startswith("weight"):
		nn.init.xavier_normal_(param)
	else:
		nn.init.zeros_(param)