简述
本文是 Pytorch封装简单RNN模型，进行中文训练及文本预测 一文的延申，主要做以下改动：
1.将nn.RNN替换为nn.LSTM，并设置多层LSTM：
既然使用pytorch了，自然不需要手动实现多层，注意nn.RNN和nn.LSTM 在实例化时均有参数num_layers来指定层数，本文设置num_layers=2；
2.新增emdedding层，替换掉原来的nn.functional.one_hot向量化，这样得到的emdedding层可以用来做词向量分布式表示；
3.在emdedding后、LSTM内部、LSTM后均增加Dropout层，来抑制过拟合：
在nn.LSTM内部的Dropout可以通过实例化时的参数dropout来设置，需要注意pytorch仅在两层lstm之间应用Dropout，不会在最后一层的LSTM输出上应用Dropout。
emdedding后、LSTM后与线性层之间则需要手动添加Dropout层。
4.考虑emdedding与最后的Linear层共享权重：
这样做可以在保证精度的情况下，减少学习参数，但本文代码没有实现该部分。
不考虑第四条时，模型结构如下：
代码
模型代码：
class MyLSTM(nn.Module):
def __init__(self, vocab_size, wordvec_size, hidden_size, num_layers=2, dropout=0.5):
super(MyLSTM, self).__init__()
self.vocab_size = vocab_size
self.word_vec_size = wordvec_size
self.hidden_size = hidden_size
self.embedding = nn.Embedding(vocab_size, wordvec_size)
self.dropout = nn.Dropout(dropout)
self.rnn = nn.LSTM(wordvec_size, hidden_size, num_layers=num_layers, dropout=dropout)
# self.rnn = rnn_layer
self.linear = nn.Linear(self.hidden_size, vocab_size)
def forward(self, x, h0=None, c0=None):
# nn.Embedding 需要的类型 (IntTensor or LongTensor) # 传过来的X是(batch_size, seq), embedding之后 是(batch_size, seq, vocab_size)
# nn.LSTM 支持的X默认为(seq, batch_size, vocab_size)
# 若想用(batch_size, seq, vocab_size)作参数, 则需要在创建self.embedding实例时指定batch_first=True
# 这里用(seq, batch_size, vocab_size) 作参数，所以先给x转置，再embedding，以便再将结果传给lstm
x = x.T
x.long()
x = self.embedding(x)
x = self.dropout(x)
outputs = self.dropout(outputs)
outputs = outputs.reshape(-1, self.hidden_size)
outputs = self.linear(outputs)
return outputs, (h0, c0)
def init_state(self, device, batch_size=1):
return (torch.zeros((self.rnn.num_layers, batch_size, self.hidden_size), device=device),
torch.zeros((self.rnn.num_layers, batch_size, self.hidden_size), device=device))
训练代码：
模型应用可以参考 Pytorch封装简单RNN模型，进行中文训练及文本预测 一文。
def start_train():
# device = torch.device("cpu")
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(f'\ndevice: {device}')
corpus, vocab = load_corpus("../data/COIG-CQIA/chengyu_qa.txt")
vocab_size = len(vocab)
wordvec_size = 100
hidden_size = 256
epochs = 1
batch_size = 50
learning_rate = 0.01
time_size = 4
max_grad_max_norm = 0.5
num_layers = 2
dropout = 0.5
dataset = make_dataset(corpus=corpus, time_size=time_size)
data_loader = data.DataLoader(dataset=dataset, batch_size=batch_size, shuffle=True)
net = MyLSTM(vocab_size=vocab_size, wordvec_size=wordvec_size, hidden_size=hidden_size, num_layers=num_layers, dropout=dropout)
net.to(device)
# print(net.state_dict())
criterion = nn.CrossEntropyLoss()
criterion.to(device)
optimizer = optim.Adam(net.parameters(), lr=learning_rate)
writer = SummaryWriter('./train_logs')
# 随便定义个输入, 好使用add_graph
tmp = torch.randint(0, 100, size=(batch_size, time_size)).to(device)
h0, c0 = net.init_state(batch_size=batch_size, device=device)
writer.add_graph(net, [tmp, h0, c0])
loss_counter = 0
total_loss = 0
ppl_list = list()
total_train_step = 0
for epoch in range(epochs):
print('------------Epoch {}/{}'.format(epoch + 1, epochs))
for X, y in data_loader:
X, y = X.to(device), y.to(device)
# 这里batch_size=X.shape[0]是因为在加载数据时, DataLoader没有设置丢弃不完整的批次, 所以存在实际批次不满足设定的batch_size
h0, c0 = net.init_state(batch_size=X.shape[0], device=device)
outputs, (hn, cn) = net(X, h0, c0)
optimizer.zero_grad()
# y也变成 时间序列*批次大小的行数, 才和 outputs 一致
y = y.T.reshape(-1)
# 交叉熵的第二个参数需要LongTorch
loss = criterion(outputs, y.long())
loss.backward()
# 求完梯度之后可以考虑梯度裁剪, 再更新梯度
grad_clipping(net, max_grad_max_norm)
optimizer.step()
total_loss += loss.item()
loss_counter += 1
total_train_step += 1
if total_train_step % 10 == 0:
print(f'Epoch: {epoch + 1}, 累计训练次数: {total_train_step}, 本次loss: {loss.item():.4f}')
writer.add_scalar('train_loss', loss.item(), total_train_step)
ppl = np.exp(total_loss / loss_counter)
ppl_list.append(ppl)
print(f'Epoch {epoch + 1} 结束, batch_loss_average: {total_loss / loss_counter}, perplexity: {ppl}')
writer.add_scalar('ppl', ppl, epoch + 1)
total_loss = 0
loss_counter = 0
torch.save(net.state_dict(), './save/epoch_{}_ppl_{}.pth'.format(epoch + 1, ppl))
writer.close()
return net, ppl_list