RNN实现

---

RNN模型

从头开始实现

初始化模型参数

#初始化模型参数
def get_params(vocab_size, num_hiddens, device):
    num_inputs = num_outputs = vocab_size
    
    def normal(shape):
        return torch.randn(size=shape, device=device) * 0.01
    
    W_xh = normal((num_inputs, num_hiddens))
    W_hh = normal((num_hiddens, num_hiddens))
    b_h = torch.zeros(num_hiddens, device=device)
    W_hq = normal((num_hiddens, num_outputs))
    b_q = torch.zeros(num_outputs, device=device)
    params = [W_xh, W_hh, b_h, W_hq, b_q]
    for param in params:
        param.requires_grad(True)
    return params

初始化时返回隐藏状态

def init_rnn_state(batch_size, num_hiddens, device):
    return (torch.zeros((batch_size, num_hiddens), device=device), ) #隐变量的维度(批量大小，隐藏单元数)

定义如何在一个时间步内计算隐藏状态和输出

#定义如何在一个时间步内计算隐藏状态和输出
def rnn(inputs, state, params):
    # inputs的形状：(时间步数量，批量大小，词表大小)
    W_xh, W_hh, b_h, W_hq, b_q = params
    H, = state
    outputs = []
    # X的形状：(批量大小，词表大小)
    for X in inputs:
        H = torch.tanh(torch.mm(X, W_xh) + torch.mm(H, W_hh) + b_h)
        Y = torch.mm(H, W_hq) + b_q
        outputs.append(Y)
    return torch.cat(outputs, dim=0), (H,) #Y 的维度(时间步数量*批量大小，词表大小)

从零开始实现的循环神经网络模型

class RNNModelScratch: 
    """从零开始实现的循环神经网络模型"""
    def __init__(self, vocab_size, num_hiddens, device,
                 get_params, init_state, forward_fn):
        self.vocab_size, self.num_hiddens = vocab_size, num_hiddens
        self.params = get_params(vocab_size, num_hiddens, device)
        self.init_state, self.forward_fn = init_state, forward_fn

    def __call__(self, X, state):
        X = F.one_hot(X.T, self.vocab_size).type(torch.float32) #X的维度(批量大小，时间步数量)-->(时间步数量，批量大小，词表大小)
        return self.forward_fn(X, state, self.params)

    def begin_state(self, batch_size, device):
        return self.init_state(batch_size, self.num_hiddens, device)

使用Pytorch简洁实现

class RNNModel(nn.Module):
    """循环神经网络模型"""
    def __init__(self, rnn_layer, vocab_size, **kwargs):
        super(RNNModel, self).__init__(**kwargs)
        self.rnn = rnn_layer
        self.vocab_size = vocab_size
        self.num_hiddens = self.rnn.hidden_size
        # 如果RNN是双向的，num_directions应该是2，否则应该是1
        if not self.rnn.bidirectional:
            self.num_directions = 1
            self.linear = nn.Linear(self.num_hiddens, self.vocab_size)
        else:
            self.num_directions = 2
            self.linear = nn.Linear(self.num_hiddens * 2, self.vocab_size)

    def forward(self, inputs, state):
        X = F.one_hot(inputs.T.long(), self.vocab_size)
        X = X.to(torch.float32)
        Y, state = self.rnn(X, state)
        # 全连接层首先将Y的形状改为(时间步数*批量大小,隐藏单元数)
        # 它的输出形状是(时间步数*批量大小,词表大小)。
        output = self.linear(Y.reshape((-1, Y.shape[-1])))
        return output, state

    def begin_state(self, device, batch_size=1): #初始化隐状态，即h0
        if not isinstance(self.rnn, nn.LSTM):
            # nn.GRU以张量作为隐状态
            return  torch.zeros((self.num_directions * self.rnn.num_layers,
                                 batch_size, self.num_hiddens),
                                device=device)
        else:
            # nn.LSTM以元组作为隐状态
            return (torch.zeros((
                self.num_directions * self.rnn.num_layers,
                batch_size, self.num_hiddens), device=device),
                    torch.zeros((
                        self.num_directions * self.rnn.num_layers,
                        batch_size, self.num_hiddens), device=device))