1. seq2seq
2. code
import collections
import math
import torch
from torch import nn
from d2l import torch as d2l
#@save
class Seq2SeqEncoder(d2l.Encoder):
"""用于序列到序列学习的循环神经网络编码器"""
def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
dropout=0, **kwargs):
super(Seq2SeqEncoder, self).__init__(**kwargs)
# 嵌入层
self.embedding = nn.Embedding(vocab_size, embed_size)
self.rnn = nn.GRU(embed_size, num_hiddens, num_layers,
dropout=dropout)
def forward(self, X, *args):
# 输出'X'的形状：(batch_size,num_steps,embed_size)
X = self.embedding(X)
# 在循环神经网络模型中，第一个轴对应于时间步
X = X.permute(1, 0, 2)
# 如果未提及状态，则默认为0
output, state = self.rnn(X)
# output的形状:(num_steps,batch_size,num_hiddens)
# state的形状:(num_layers,batch_size,num_hiddens)
return output, state
encoder = Seq2SeqEncoder(vocab_size=10, embed_size=8, num_hiddens=16,
num_layers=2)
encoder.eval()
X = torch.zeros((4, 7), dtype=torch.long)
output, state = encoder(X)
output.shape
state.shape
class Seq2SeqDecoder(d2l.Decoder):
"""用于序列到序列学习的循环神经网络解码器"""
def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
dropout=0, **kwargs):
super(Seq2SeqDecoder, self).__init__(**kwargs)
self.embedding = nn.Embedding(vocab_size, embed_size)
self.rnn = nn.GRU(embed_size + num_hiddens, num_hiddens, num_layers,
dropout=dropout)
self.dense = nn.Linear(num_hiddens, vocab_size)
def init_state(self, enc_outputs, *args):
return enc_outputs[1]
def forward(self, X, state):
# 输出'X'的形状：(batch_size,num_steps,embed_size)
X = self.embedding(X).permute(1, 0, 2)
# 广播context，使其具有与X相同的num_steps
context = state[-1].repeat(X.shape[0], 1, 1)
X_and_context = torch.cat((X, context), 2)
output, state = self.rnn(X_and_context, state)
output = self.dense(output).permute(1, 0, 2)
# output的形状:(batch_size,num_steps,vocab_size)
# state的形状:(num_layers,batch_size,num_hiddens)
return output, state
decoder = Seq2SeqDecoder(vocab_size=10, embed_size=8, num_hiddens=16,
num_layers=2)
decoder.eval()
state = decoder.init_state(encoder(X))
output, state = decoder(X, state)
output.shape, state.shape
#@save
def sequence_mask(X, valid_len, value=0):
"""在序列中屏蔽不相关的项"""
maxlen = X.size(1)
mask = torch.arange((maxlen), dtype=torch.float32,
device=X.device)[None, :] < valid_len[:, None]
X[~mask] = value
return X
X = torch.tensor([[1, 2, 3], [4, 5, 6]])
sequence_mask(X, torch.tensor([1, 2]))
X = torch.ones(2, 3, 4)
sequence_mask(X, torch.tensor([1, 2]), value=-1)
#@save
class MaskedSoftmaxCELoss(nn.CrossEntropyLoss):
"""带遮蔽的softmax交叉熵损失函数"""
# pred的形状：(batch_size,num_steps,vocab_size)
# label的形状：(batch_size,num_steps)
# valid_len的形状：(batch_size,)
def forward(self, pred, label, valid_len):
weights = torch.ones_like(label)
weights = sequence_mask(weights, valid_len)
self.reduction='none'
unweighted_loss = super(MaskedSoftmaxCELoss, self).forward(
pred.permute(0, 2, 1), label)
weighted_loss = (unweighted_loss * weights).mean(dim=1)
return weighted_loss
loss = MaskedSoftmaxCELoss()
loss(torch.ones(3, 4, 10), torch.ones((3, 4), dtype=torch.long),
torch.tensor([4, 2, 0]))
#@save
def train_seq2seq(net, data_iter, lr, num_epochs, tgt_vocab, device):
"""训练序列到序列模型"""
def xavier_init_weights(m):
if type(m) == nn.Linear:
nn.init.xavier_uniform_(m.weight)
if type(m) == nn.GRU:
for param in m._flat_weights_names:
if "weight" in param:
nn.init.xavier_uniform_(m._parameters[param])
net.apply(xavier_init_weights)
net.to(device)
optimizer = torch.optim.Adam(net.parameters(), lr=lr)
loss = MaskedSoftmaxCELoss()
net.train()
animator = d2l.Animator(xlabel='epoch', ylabel='loss',
xlim=[10, num_epochs])
for epoch in range(num_epochs):
timer = d2l.Timer()
metric = d2l.Accumulator(2) # 训练损失总和，词元数量
for batch in data_iter:
optimizer.zero_grad()
X, X_valid_len, Y, Y_valid_len = [x.to(device) for x in batch]
bos = torch.tensor([tgt_vocab['<bos>']] * Y.shape[0],
device=device).reshape(-1, 1)
dec_input = torch.cat([bos, Y[:, :-1]], 1) # 强制教学
Y_hat, _ = net(X, dec_input, X_valid_len)
l = loss(Y_hat, Y, Y_valid_len)
l.sum().backward() # 损失函数的标量进行“反向传播”
d2l.grad_clipping(net, 1)
num_tokens = Y_valid_len.sum()
optimizer.step()
with torch.no_grad():
metric.add(l.sum(), num_tokens)
if (epoch + 1) % 10 == 0:
animator.add(epoch + 1, (metric[0] / metric[1],))
print(f'loss {metric[0] / metric[1]:.3f}, {metric[1] / timer.stop():.1f} '
f'tokens/sec on {str(device)}')
#@save
def predict_seq2seq(net, src_sentence, src_vocab, tgt_vocab, num_steps,
device, save_attention_weights=False):
"""序列到序列模型的预测"""
# 在预测时将net设置为评估模式
net.eval()
src_tokens = src_vocab[src_sentence.lower().split(' ')] + [
src_vocab['<eos>']]
enc_valid_len = torch.tensor([len(src_tokens)], device=device)
src_tokens = d2l.truncate_pad(src_tokens, num_steps, src_vocab['<pad>'])
# 添加批量轴
enc_X = torch.unsqueeze(
torch.tensor(src_tokens, dtype=torch.long, device=device), dim=0)
enc_outputs = net.encoder(enc_X, enc_valid_len)
dec_state = net.decoder.init_state(enc_outputs, enc_valid_len)
# 添加批量轴
dec_X = torch.unsqueeze(torch.tensor(
[tgt_vocab['<bos>']], dtype=torch.long, device=device), dim=0)
output_seq, attention_weight_seq = [], []
for _ in range(num_steps):
Y, dec_state = net.decoder(dec_X, dec_state)
# 我们使用具有预测最高可能性的词元，作为解码器在下一时间步的输入
dec_X = Y.argmax(dim=2)
pred = dec_X.squeeze(dim=0).type(torch.int32).item()
# 保存注意力权重（稍后讨论）
if save_attention_weights:
attention_weight_seq.append(net.decoder.attention_weights)
# 一旦序列结束词元被预测，输出序列的生成就完成了
if pred == tgt_vocab['<eos>']:
break
output_seq.append(pred)
return ' '.join(tgt_vocab.to_tokens(output_seq)), attention_weight_seq
def bleu(pred_seq, label_seq, k): #@save
"""计算BLEU"""
pred_tokens, label_tokens = pred_seq.split(' '), label_seq.split(' ')
len_pred, len_label = len(pred_tokens), len(label_tokens)
score = math.exp(min(0, 1 - len_label / len_pred))
for n in range(1, k + 1):
num_matches, label_subs = 0, collections.defaultdict(int)
for i in range(len_label - n + 1):
label_subs[' '.join(label_tokens[i: i + n])] += 1
for i in range(len_pred - n + 1):
if label_subs[' '.join(pred_tokens[i: i + n])] > 0:
num_matches += 1
label_subs[' '.join(pred_tokens[i: i + n])] -= 1
score *= math.pow(num_matches / (len_pred - n + 1), math.pow(0.5, n))
return score
engs = ['go .', "i lost .", 'he\'s calm .', 'i\'m home .']
fras = ['va !', 'j\'ai perdu .', 'il est calme .', 'je suis chez moi .']
for eng, fra in zip(engs, fras):
translation, attention_weight_seq = predict_seq2seq(
net, eng, src_vocab, tgt_vocab, num_steps, device)
print(f'{eng} => {translation}, bleu {bleu(translation, fra, k=2):.3f}')
3. QA
3 encoder输入embedding_size,输出位hindersize 不能直接按位相加，长度不一样。
4 不是。 word2vec用的不多了。embedding是重新初始化，开始训练的。
5 encoder output没意义。decoder output是预测
6 实际句子的长度，算loss、attention不看padding的内容
9 时代的洪流
10 学过不等于会用 what how why
11 不能放到下一条句子。通常取相对较长的句子，不截掉太多。
12 decoder不一定是seq2seq，文字生成图片，decoder可以是cnn，不用输入。
