介绍

假设 $X_t∈\R^{n×d}$ 是时间步 $t$ 的小批量输入， $H_t∈\R^{n×h}$ 是该时间步的隐藏变量，则：

$H_t=ϕ(X_t W_{xh}+H_{t−1}W_{hh}+b_h)$

其中， $W_{xh}∈\R^{d×h}$ ， $W_{hh}∈\R^{h×h}$ ， $b_h∈\R^{1×h}$ ， $ϕ$ 函数是非线性激活函数。由于引入了 $H_{t−1}W_{hh}$ ， $H_t$ 能够捕捉截至当前时间步的序列的历史信息，就像是神经网络当前时间步的状态或记忆一样。由于 $H_t$ 的计算基于 $H_{t−1}$ ，上式的计算是循环的，使用循环计算的网络即循环神经网络（recurrent neural network）。
在时间步 t ，输出层的输出为：

$O_t=H_tW_{hq}+b_q$
其中 $W_{hq}∈\R^{h×q} ， b_q∈\R^{1×q}$ 。

定义模型

使用Pytorch中的nn.RNN来构造循环神经网络。在本节中，我们主要关注nn.RNN的以下几个构造函数参数：

input_size - The number of expected features in the input x
hidden_size – The number of features in the hidden state h
nonlinearity – The non-linearity to use. Can be either ‘tanh’ or ‘relu’. Default: ‘tanh’
batch_first – If True, then the input and output tensors are provided as (batch_size, num_steps, input_size). Default: False

这里的batch_first决定了输入的形状，我们使用默认的参数False，对应的输入形状是 (num_steps, batch_size, input_size)。

forward函数的参数为：

input of shape (num_steps, batch_size, input_size): tensor containing the features of the input sequence.
h_0 of shape (num_layers * num_directions, batch_size, hidden_size): tensor containing the initial hidden state for each element in the batch. Defaults to zero if not provided. If the RNN is bidirectional, num_directions should be 2, else it should be 1.

forward函数的返回值是：

output of shape (num_steps, batch_size, num_directions * hidden_size): tensor containing the output features (h_t) from the last layer of the RNN, for each t.
h_n of shape (num_layers * num_directions, batch_size, hidden_size): tensor containing the hidden state for t = num_steps.

现在我们构造一个nn.RNN实例，并用一个简单的例子来看一下输出的形状。

rnn_layer = nn.RNN(input_size=vocab_size, hidden_size=num_hiddens)
num_steps, batch_size = 35, 2
X = torch.rand(num_steps, batch_size, vocab_size)
state = None
Y, state_new = rnn_layer(X, state)
print(Y.shape, state_new.shape)

torch.Size([35, 2, 256]) torch.Size([1, 2, 256])

我们定义一个完整的基于循环神经网络的语言模型。

class RNNModel(nn.Module):
    def __init__(self, rnn_layer, vocab_size):
        super(RNNModel, self).__init__()
        self.rnn = rnn_layer
        self.hidden_size = rnn_layer.hidden_size * (2 if rnn_layer.bidirectional else 1) 
        self.vocab_size = vocab_size
        self.dense = nn.Linear(self.hidden_size, vocab_size)

    def forward(self, inputs, state):
        # inputs.shape: (batch_size, num_steps)
        X = to_onehot(inputs, vocab_size)
        X = torch.stack(X)  # X.shape: (num_steps, batch_size, vocab_size)
        hiddens, state = self.rnn(X, state)
        hiddens = hiddens.view(-1, hiddens.shape[-1])  # hiddens.shape: (num_steps * batch_size, hidden_size)
        output = self.dense(hiddens)
        return output, state

类似的，我们需要实现一个预测函数，与前面的区别在于前向计算和初始化隐藏状态。

def predict_rnn_pytorch(prefix, num_chars, model, vocab_size, device, idx_to_char,
                      char_to_idx):
    state = None
    output = [char_to_idx[prefix[0]]]  # output记录prefix加上预测的num_chars个字符
    for t in range(num_chars + len(prefix) - 1):
        X = torch.tensor([output[-1]], device=device).view(1, 1)
        (Y, state) = model(X, state)  # 前向计算不需要传入模型参数
        if t < len(prefix) - 1:
            output.append(char_to_idx[prefix[t + 1]])
        else:
            output.append(Y.argmax(dim=1).item())
    return ''.join([idx_to_char[i] for i in output])

使用权重为随机值的模型来预测一次。

model = RNNModel(rnn_layer, vocab_size).to(device)
predict_rnn_pytorch('分开', 10, model, vocab_size, device, idx_to_char, char_to_idx)

输出： ‘分开胸呵以轮轮轮轮轮轮轮’

接下来实现训练函数，这里只使用了相邻采样。

def train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
                                corpus_indices, idx_to_char, char_to_idx,
                                num_epochs, num_steps, lr, clipping_theta,
                                batch_size, pred_period, pred_len, prefixes):
    loss = nn.CrossEntropyLoss()
    optimizer = torch.optim.Adam(model.parameters(), lr=lr)
    model.to(device)
    for epoch in range(num_epochs):
        l_sum, n, start = 0.0, 0, time.time()
        data_iter = d2l.data_iter_consecutive(corpus_indices, batch_size, num_steps, device) # 相邻采样
        state = None
        for X, Y in data_iter:
            if state is not None:
                # 使用detach函数从计算图分离隐藏状态
                if isinstance (state, tuple): # LSTM, state:(h, c)  
                    state[0].detach_()
                    state[1].detach_()
                else: 
                    state.detach_()
            (output, state) = model(X, state) # output.shape: (num_steps * batch_size, vocab_size)
            y = torch.flatten(Y.T)
            l = loss(output, y.long())
            
            optimizer.zero_grad()
            l.backward()
            grad_clipping(model.parameters(), clipping_theta, device)
            optimizer.step()
            l_sum += l.item() * y.shape[0]
            n += y.shape[0]
        

        if (epoch + 1) % pred_period == 0:
            print('epoch %d, perplexity %f, time %.2f sec' % (
                epoch + 1, math.exp(l_sum / n), time.time() - start))
            for prefix in prefixes:
                print(' -', predict_rnn_pytorch(prefix, pred_len, model,vocab_size, device, idx_to_char,char_to_idx))

训练模型

num_epochs, batch_size, lr, clipping_theta = 250, 32, 1e-3, 1e-2
pred_period, pred_len, prefixes = 50, 50, ['分开', '不分开']
train_and_predict_rnn_pytorch(model, num_hiddens, vocab_size, device,
                            corpus_indices, idx_to_char, char_to_idx,
                            num_epochs, num_steps, lr, clipping_theta,
                            batch_size, pred_period, pred_len, prefixes)