RNN GRU LSTM 区别

RNN网络

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

    # 隐藏层参数
    W_xh = normal((num_inputs, num_hiddens))
    W_hh = normal((num_hiddens, num_hiddens))
    b_h = torch.zeros(num_hiddens, device=device)
    # 输出层参数
    W_hq = normal((num_hiddens, num_outputs))
    b_q = torch.zeros(num_outputs, device=device)
    # 附加梯度
    params = [W_xh, W_hh, b_h, W_hq, b_q]
    for param in params:
        param.requires_grad_(True)
    return params
    
def init_rnn_state(batch_size, num_hiddens, device):
    return (torch.zeros((batch_size, num_hiddens), device=device), )

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,)

GRU网络

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

   def three():
       return (normal((num_inputs, num_hiddens)),
               normal((num_hiddens, num_hiddens)),
               torch.zeros(num_hiddens, device=device))

   W_xz, W_hz, b_z = three()  # 更新门参数
   W_xr, W_hr, b_r = three()  # 重置门参数
   W_xh, W_hh, b_h = three()  # 候选隐状态参数
   # 输出层参数
   W_hq = normal((num_hiddens, num_outputs))
   b_q = torch.zeros(num_outputs, device=device)
   # 附加梯度
   params = [W_xz, W_hz, b_z, W_xr, W_hr, b_r, W_xh, W_hh, b_h, W_hq, b_q]
   for param in params:
       param.requires_grad_(True)
   return params

def init_gru_state(batch_size, num_hiddens, device):
   return (torch.zeros((batch_size, num_hiddens), device=device), )

def gru(inputs, state, params):
   W_xz, W_hz, b_z, W_xr, W_hr, b_r, W_xh, W_hh, b_h, W_hq, b_q = params
   H, = state
   outputs = []
   for X in inputs:
       Z = torch.sigmoid((X @ W_xz) + (H @ W_hz) + b_z)
       R = torch.sigmoid((X @ W_xr) + (H @ W_hr) + b_r)
       H_tilda = torch.tanh((X @ W_xh) + ((R * H) @ W_hh) + b_h)
       H = Z * H + (1 - Z) * H_tilda
       Y = H @ W_hq + b_q
       outputs.append(Y)
   return torch.cat(outputs, dim=0), (H,)

LSTM网络

def get_lstm_params(vocab_size, num_hiddens, device):
    num_inputs = num_outputs = vocab_size

    def normal(shape):
        return torch.randn(size=shape, device=device)*0.01

    def three():
        return (normal((num_inputs, num_hiddens)),
                normal((num_hiddens, num_hiddens)),
                torch.zeros(num_hiddens, device=device))

    W_xi, W_hi, b_i = three()  # 输入门参数
    W_xf, W_hf, b_f = three()  # 遗忘门参数
    W_xo, W_ho, b_o = three()  # 输出门参数
    W_xc, W_hc, b_c = three()  # 候选记忆元参数
    # 输出层参数
    W_hq = normal((num_hiddens, num_outputs))
    b_q = torch.zeros(num_outputs, device=device)
    # 附加梯度
    params = [W_xi, W_hi, b_i, W_xf, W_hf, b_f, W_xo, W_ho, b_o, W_xc, W_hc,
              b_c, W_hq, b_q]
    for param in params:
        param.requires_grad_(True)
    return params

def init_lstm_state(batch_size, num_hiddens, device):
    return (torch.zeros((batch_size, num_hiddens), device=device),
            torch.zeros((batch_size, num_hiddens), device=device))

def lstm(inputs, state, params):
    [W_xi, W_hi, b_i, W_xf, W_hf, b_f, W_xo, W_ho, b_o, W_xc, W_hc, b_c,
     W_hq, b_q] = params
    (H, C) = state
    outputs = []
    for X in inputs:
        I = torch.sigmoid((X @ W_xi) + (H @ W_hi) + b_i)
        F = torch.sigmoid((X @ W_xf) + (H @ W_hf) + b_f)
        O = torch.sigmoid((X @ W_xo) + (H @ W_ho) + b_o)
        C_tilda = torch.tanh((X @ W_xc) + (H @ W_hc) + b_c)
        C = F * C + I * C_tilda
        H = O * torch.tanh(C)
        Y = (H @ W_hq) + b_q
        outputs.append(Y)
    return torch.cat(outputs, dim=0), (H, C)

以上转自沐神动手学深度学习书中