循环神经网络

import torch
import torch.nn as nn
import time
import math
import sys
sys.path.append("/home/kesci/input")
import d2l_jay9460 as d2l
(corpus_indices, char_to_idx, idx_to_char, vocab_size) = d2l.load_data_jay_lyrics()
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

def one_hot(x, n_class, dtype=torch.float32):
    result = torch.zeros(x.shape[0], n_class, dtype=dtype, device=x.device)  # shape: (n, n_class)
    result.scatter_(1, x.long().view(-1, 1), 1)  # result[i, x[i, 0]] = 1
    return result
    
x = torch.tensor([0, 2])
x_one_hot = one_hot(x, vocab_size)
print(x_one_hot)
print(x_one_hot.shape)
print(x_one_hot.sum(axis=1))

def to_onehot(X, n_class):
    return [one_hot(X[:, i], n_class) for i in range(X.shape[1])]

X = torch.arange(10).view(2, 5)
inputs = to_onehot(X, vocab_size)
print(len(inputs), inputs[0].shape)

初始化模型参数

num_inputs, num_hiddens, num_outputs = vocab_size, 256, vocab_size
# num_inputs: d
# num_hiddens: h, 隐藏单元的个数是超参数
# num_outputs: q

def get_params():
    def _one(shape):
        param = torch.zeros(shape, device=device, dtype=torch.float32)
        nn.init.normal_(param, 0, 0.01)
        return torch.nn.Parameter(param)

    # 隐藏层参数
    W_xh = _one((num_inputs, num_hiddens))
    W_hh = _one((num_hiddens, num_hiddens))
    b_h = torch.nn.Parameter(torch.zeros(num_hiddens, device=device))
    # 输出层参数
    W_hq = _one((num_hiddens, num_outputs))
    b_q = torch.nn.Parameter(torch.zeros(num_outputs, device=device))
    return (W_xh, W_hh, b_h, W_hq, b_q)

定义模型

函数rnn用循环的方式依次完成循环神经网络每个时间步的计算。

def rnn(inputs, state, params):
    # inputs和outputs皆为num_steps个形状为(batch_size, vocab_size)的矩阵
    W_xh, W_hh, b_h, W_hq, b_q = params
    H, = state
    outputs = []
    for X in inputs:
        H = torch.tanh(torch.matmul(X, W_xh) + torch.matmul(H, W_hh) + b_h)
        Y = torch.matmul(H, W_hq) + b_q
        outputs.append(Y)
    return outputs, (H,)

函数init_rnn_state初始化隐藏变量，这里的返回值是一个元组。

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

做个简单的测试来观察输出结果的个数（时间步数），以及第一个时间步的输出层输出的形状和隐藏状态的形状。

print(X.shape)
print(num_hiddens)
print(vocab_size)
state = init_rnn_state(X.shape[0], num_hiddens, device)
inputs = to_onehot(X.to(device), vocab_size)
params = get_params()
outputs, state_new = rnn(inputs, state, params)
print(len(inputs), inputs[0].shape)
print(len(outputs), outputs[0].shape)
print(len(state), state[0].shape)
print(len(state_new), state_new[0].shape)

def grad_clipping(params, theta, device):
    norm = torch.tensor([0.0], device=device)
    for param in params:
        norm += (param.grad.data ** 2).sum()
    norm = norm.sqrt().item()
    if norm > theta:
        for param in params:
            param.grad.data *= (theta / norm)

定义预测函数

以下函数基于前缀prefix（含有数个字符的字符串）来预测接下来的num_chars个字符。这个函数稍显复杂，其中我们将循环神经单元rnn设置成了函数参数，这样在后面小节介绍其他循环神经网络时能重复使用这个函数。

def predict_rnn(prefix, num_chars, rnn, params, init_rnn_state,
                num_hiddens, vocab_size, device, idx_to_char, char_to_idx):
    state = init_rnn_state(1, num_hiddens, device)
    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):
        # 将上一时间步的输出作为当前时间步的输入
        X = to_onehot(torch.tensor([[output[-1]]], device=device), vocab_size)
        # 计算输出和更新隐藏状态
        (Y, state) = rnn(X, state, params)
        # 下一个时间步的输入是prefix里的字符或者当前的最佳预测字符
        if t < len(prefix) - 1:
            output.append(char_to_idx[prefix[t + 1]])
        else:
            output.append(Y[0].argmax(dim=1).item())
    return ''.join([idx_to_char[i] for i in output])

我们先测试一下predict_rnn函数。我们将根据前缀“分开”创作长度为10个字符（不考虑前缀长度）的一段歌词。因为模型参数为随机值，所以预测结果也是随机的。

predict_rnn('分开', 10, rnn, params, init_rnn_state, num_hiddens, vocab_size,
            device, idx_to_char, char_to_idx)

def train_and_predict_rnn(rnn, get_params, init_rnn_state, num_hiddens,
                          vocab_size, device, corpus_indices, idx_to_char,
                          char_to_idx, is_random_iter, num_epochs, num_steps,
                          lr, clipping_theta, batch_size, pred_period,
                          pred_len, prefixes):
    if is_random_iter:
        data_iter_fn = d2l.data_iter_random
    else:
        data_iter_fn = d2l.data_iter_consecutive
    params = get_params()
    loss = nn.CrossEntropyLoss()

    for epoch in range(num_epochs):
        if not is_random_iter:  # 如使用相邻采样，在epoch开始时初始化隐藏状态
            state = init_rnn_state(batch_size, num_hiddens, device)
        l_sum, n, start = 0.0, 0, time.time()
        data_iter = data_iter_fn(corpus_indices, batch_size, num_steps, device)
        for X, Y in data_iter:
            if is_random_iter:  # 如使用随机采样，在每个小批量更新前初始化隐藏状态
                state = init_rnn_state(batch_size, num_hiddens, device)
            else:  # 否则需要使用detach函数从计算图分离隐藏状态
                for s in state:
                    s.detach_()
            # inputs是num_steps个形状为(batch_size, vocab_size)的矩阵
            inputs = to_onehot(X, vocab_size)
            # outputs有num_steps个形状为(batch_size, vocab_size)的矩阵
            (outputs, state) = rnn(inputs, state, params)
            # 拼接之后形状为(num_steps * batch_size, vocab_size)
            outputs = torch.cat(outputs, dim=0)
            # Y的形状是(batch_size, num_steps)，转置后再变成形状为
            # (num_steps * batch_size,)的向量，这样跟输出的行一一对应
            y = torch.flatten(Y.T)
            # 使用交叉熵损失计算平均分类误差
            l = loss(outputs, y.long())
            
            # 梯度清0
            if params[0].grad is not None:
                for param in params:
                    param.grad.data.zero_()
            l.backward()
            grad_clipping(params, clipping_theta, device)  # 裁剪梯度
            d2l.sgd(params, lr, 1)  # 因为误差已经取过均值，梯度不用再做平均
            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(prefix, pred_len, rnn, params, init_rnn_state,
                    num_hiddens, vocab_size, device, idx_to_char, char_to_idx))

训练模型并创作歌词

现在我们可以训练模型了。首先，设置模型超参数。我们将根据前缀“分开”和“不分开”分别创作长度为50个字符（不考虑前缀长度）的一段歌词。我们每过50个迭代周期便根据当前训练的模型创作一段歌词。

num_epochs, num_steps, batch_size, lr, clipping_theta = 250, 35, 32, 1e2, 1e-2
pred_period, pred_len, prefixes = 50, 50, ['分开', '不分开']

下面采用随机采样训练模型并创作歌词。

train_and_predict_rnn(rnn, get_params, init_rnn_state, num_hiddens,
                      vocab_size, device, corpus_indices, idx_to_char,
                      char_to_idx, True, num_epochs, num_steps, lr,
                      clipping_theta, batch_size, pred_period, pred_len,
                      prefixes)

接下来采用相邻采样训练模型并创作歌词。

train_and_predict_rnn(rnn, get_params, init_rnn_state, num_hiddens,
                      vocab_size, device, corpus_indices, idx_to_char,
                      char_to_idx, False, num_epochs, num_steps, lr,
                      clipping_theta, batch_size, pred_period, pred_len,
                      prefixes)

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)

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)

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)