用代码实现RNN(循环神经网络)

在这次的笔记中，我们以自然语言处理中二分类的例子，用pytorch框架将RNN实现一遍。
结核如下图：

首先手动实现：

class RNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size):
        super(RNN, self).__init__()
        self.hidden_size = hidden_size
        self.input_size = input_size
        # embedding layer
        self.embed = nn.Embedding(input_size, hidden_size)
        #hidden layer, attention to the size of input: 2*hidden_size
        self.i2h = nn.Linear(2*hidden_size, hidden_size)
        #output layer
        self.i20 = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax()
    def forward(self, input, hidden):
        x = self.embed(input)
        combined = torch.cat((x,hidden),1)
        hidden = self.i2h(combined)
        output = self.i2o(hidden)
        return output, hidden
    def initHidden(self):
        return Variable(torch.zeros(self.input_size, self.hidden_size))

下面我们再用pytorch里原有的层来实现：

class SimpleRNN(nn.Module):
    def __init__(self, input_size, hidden_size, output_size, num_layers=1):
        super(SimpleRNN,self).__init__()
        self.hidden_size = hidden_size
        self.num_layers = num_layers
        self.embedding = nn.Embedding(input_size, hidden_size)
        self.rnn = nn.RNN(hidden_size, hidden_size, num_layers,batch_first=True)
        self.fc = nn.Linear(hidden_size, output_size)
        self.softmax = nn.LogSoftmax()
    def forward(self, input, hidden):
        x = self.embedding(input)
        output, hidden = self.rnn(x,hidden)
        output = output[:,-1,:]# get the lastest ouput
        output = self.fc(output)
        output = self.softmax(output)
        return output,hidden