本文主要介绍一下如何使用 PyTorch 复现 Transformer,实现简单的机器翻译任务。
数据预处理
这里我并没有用什么大型的数据集,而是手动输入了两对德语→英语的句子,还有每个字的索引也是我手动硬编码上去的,主要是为了降低代码阅读难度,我希望读者能更关注模型实现的部分
import math
import torch
import numpy as np
import torch.nn as nn
import torch.optim as optim
import torch.utils.data as Data
# S: Symbol that shows starting of decoding input
# E: Symbol that shows starting of decoding output
# P: Symbol that will fill in blank sequence if current batch data size is short than time steps
sentences = [
# enc_input dec_input dec_output
['ich mochte ein bier P', 'S i want a beer .', 'i want a beer . E'],
['ich mochte ein cola P', 'S i want a coke .', 'i want a coke . E']
]
# Padding Should be Zero
src_vocab = {'P' : 0, 'ich' : 1, 'mochte' : 2, 'ein' : 3, 'bier' : 4, 'cola' : 5}
src_vocab_size = len(src_vocab)
tgt_vocab = {'P' : 0, 'i' : 1, 'want' : 2, 'a' : 3, 'beer' : 4, 'coke' : 5, 'S' : 6, 'E' : 7, '.' : 8}
idx2word = {i: w for i, w in enumerate(tgt_vocab)}
tgt_vocab_size = len(tgt_vocab)
src_len = 5 # enc_input max sequence length
tgt_len = 6 # dec_input(=dec_output) max sequence length
def make_data(sentences):
enc_inputs, dec_inputs, dec_outputs = [], [], []
for i in range(len(sentences)):
enc_input = [[src_vocab[n] for n in sentences[i][0].split()]] # [[1, 2, 3, 4, 0], [1, 2, 3, 5, 0]]
dec_input = [[tgt_vocab[n] for n in sentences[i][1].split()]] # [[6, 1, 2, 3, 4, 8], [6, 1, 2, 3, 5, 8]]
dec_output = [[tgt_vocab[n] for n in sentences[i][2].split()]] # [[1, 2, 3, 4, 8, 7], [1, 2, 3, 5, 8, 7]]
enc_inputs.extend(enc_input)
dec_inputs.extend(dec_input)
dec_outputs.extend(dec_output)
return torch.LongTensor(enc_inputs), torch.LongTensor(dec_inputs), torch.LongTensor(dec_outputs)
enc_inputs, dec_inputs, dec_outputs = make_data(sentences)
class MyDataSet(Data.Dataset):
def __init__(self, enc_inputs, dec_inputs, dec_outputs):
super(MyDataSet, self).__init__()
self.enc_inputs = enc_inputs
self.dec_inputs = dec_inputs
self.dec_outputs = dec_outputs
def __len__(self):
return self.enc_inputs.shape[0]
def __getitem__(self, idx):
return self.enc_inputs[idx], self.dec_inputs[idx], self.dec_outputs[idx]
loader = Data.DataLoader(MyDataSet(enc_inputs, dec_inputs, dec_outputs), 2, True)
模型参数
# Transformer Parameters
d_model = 512 # Embedding Size
d_ff = 2048 # FeedForward dimension
d_k = d_v = 64 # dimension of K(=Q), V
n_layers = 6 # number of Encoder of Decoder Layer
n_heads = 8 # number of heads in Multi-Head Attention
上面都比较简单,下面开始涉及到模型就比较复杂了,因此我会将模型拆分成以下几个部分进行讲解
- Positional Encoding
- Pad Mask(针对句子不够长,加了 pad,因此需要对 pad 进行 mask)
- Subsequence Mask(Decoder input 不能看到未来时刻单词信息,因此需要 mask
- ScaledDotProductAttention(计算 context vector
- Multi-Head Attention
- FeedForward Layer
- Encoder Layer
- Encoder
- Decoder Layer
- Decoder
- Transformer
Positional Encoding
class PositionalEncoding(nn.Module):
def __init__(self, d_model, dropout=0.1, max_len=5000):
super(PositionalEncoding, self).__init__()
self.dropout = nn.Dropout(p=dropout)
pe = torch.zeros(max_len, d_model)
position = torch.arange(0, max_len, dtype=torch.float).unsqueeze(1)
div_term = torch.exp(torch.arange(0, d_model, 2).float() * (-math.log(10000.0) / d_model))
pe[:, 0::2] = torch.sin(position * div_term)
pe[:, 1::2] = torch.cos(position * div_term)
pe = pe.unsqueeze(0).transpose(0, 1)
self.register_buffer('pe', pe)
def forward(self, x):
'''
x: [seq_len, batch_size, d_model]
'''
x = x + self.pe[:x.size(0), :]
return self.dropout(x)
Pad Mask
def get_attn_pad_mask(seq_q, seq_k):
'''
seq_q: [batch_size, seq_len]
seq_k: [batch_size, seq_len]
seq_len could be src_len or it could be tgt_len
seq_len in seq_q and seq_len in seq_k maybe not equal
'''
batch_size, len_q = seq_q.size()
batch_size, len_k = seq_k.size()
# eq(zero) is PAD token
pad_attn_mask = seq_k.data.eq(0).unsqueeze(1) # [batch_size, 1, len_k], False is masked
return pad_attn_mask.expand(batch_size, len_q, len_k) # [batch_size, len_q, len_k]
Subsequence Mask
def get_attn_subsequence_mask(seq):
'''
seq: [batch_size, tgt_len]
'''
attn_shape = [seq.size(0), seq.size(1), seq.size(1)]
subsequence_mask = np.triu(np.ones(attn_shape), k=1) # Upper triangular matrix
subsequence_mask = torch.from_numpy(subsequence_mask).byte()
return subsequence_mask # [batch_size, tgt_len, tgt_len]
Subsequence Mask 只有 Decoder 会用到,主要作用是屏蔽未来时刻单词的信息。首先通过 np.ones()
生成一个全 1 的方阵,然后通过 np.triu()
生成一个上三角矩阵
ScaledDotProductAttention
class ScaledDotProductAttention(nn.Module):
def __init__(self):
super(ScaledDotProductAttention, self).__init__()
def forward(self, Q, K, V, attn_mask):
'''
Q: [batch_size, n_heads, len_q, d_k]
K: [batch_size, n_heads, len_k, d_k]
V: [batch_size, n_heads, len_v(=len_k), d_v]
attn_mask: [batch_size, n_heads, seq_len, seq_len]
'''
scores = torch.matmul(Q, K.transpose(-1, -2)) / np.sqrt(d_k) # scores : [batch_size, n_heads, len_q, len_k]
scores.masked_fill_(attn_mask, -1e9) # Fills elements of self tensor with value where mask is True.
attn = nn.Softmax(dim=-1)(scores)
context = torch.matmul(attn, V) # [batch_size, n_heads, len_q, d_v]
return context, attn
这里要做的是,通过Q
和K
计算出scores
,然后将scores
和 V
相乘,得到每个单词的context vector
class MultiHeadAttention(nn.Module):
def __init__(self):
super(MultiHeadAttention, self).__init__()
self.W_Q = nn.Linear(d_model, d_k * n_heads, bias=False)
self.W_K = nn.Linear(d_model, d_k * n_heads, bias=False)
self.W_V = nn.Linear(d_model, d_v * n_heads, bias=False)
self.fc = nn.Linear(n_heads * d_v, d_model, bias=False)
def forward(self, input_Q, input_K, input_V, attn_mask):
'''
input_Q: [batch_size, len_q, d_model]
input_K: [batch_size, len_k, d_model]
input_V: [batch_size, len_v(=len_k), d_model]
attn_mask: [batch_size, seq_len, seq_len]
'''
residual, batch_size = input_Q, input_Q.size(0)
# (B, S, D) -proj-> (B, S, D_new) -split-> (B, S, H, W) -trans-> (B, H, S, W)
Q = self.W_Q(input_Q).view(batch_size, -1, n_heads, d_k).transpose(1,2) # Q: [batch_size, n_heads, len_q, d_k]
K = self.W_K(input_K).view(batch_size, -1, n_heads, d_k).transpose(1,2) # K: [batch_size, n_heads, len_k, d_k]
V = self.W_V(input_V).view(batch_size, -1, n_heads, d_v).transpose(1,2) # V: [batch_size, n_heads, len_v(=len_k), d_v]
attn_mask = attn_mask.unsqueeze(1).repeat(1, n_heads, 1, 1) # attn_mask : [batch_size, n_heads, seq_len, seq_len]
# context: [batch_size, n_heads, len_q, d_v], attn: [batch_size, n_heads, len_q, len_k]
context, attn = ScaledDotProductAttention()(Q, K, V, attn_mask)
context = context.transpose(1, 2).reshape(batch_size, -1, n_heads * d_v) # context: [batch_size, len_q, n_heads * d_v]
output = self.fc(context) # [batch_size, len_q, d_model]
return nn.LayerNorm(d_model).cuda()(output + residual), attn
完整代码中一定会有三处地方调用 MultiHeadAttention()
,Encoder Layer 调用一次,传入的 input_Q、input_K、input_V
全部都是 enc_inputs
;Decoder Layer 中两次调用,第一次传入的全是 dec_inputs
,第二次传入的分别是 dec_outputs,enc_outputs,enc_outputs
FeedForward Layer
class PoswiseFeedForwardNet(nn.Module):
def __init__(self):
super(PoswiseFeedForwardNet, self).__init__()
self.fc = nn.Sequential(
nn.Linear(d_model, d_ff, bias=False),
nn.ReLU(),
nn.Linear(d_ff, d_model, bias=False)
)
def forward(self, inputs):
'''
inputs: [batch_size, seq_len, d_model]
'''
residual = inputs
output = self.fc(inputs)
return nn.LayerNorm(d_model).cuda()(output + residual) # [batch_size, seq_len, d_model]
这段代码非常简单,就是做两次线性变换,残差连接后再跟一个 Layer Norm
Encoder Layer
class EncoderLayer(nn.Module):
def __init__(self):
super(EncoderLayer, self).__init__()
self.enc_self_attn = MultiHeadAttention()
self.pos_ffn = PoswiseFeedForwardNet()
def forward(self, enc_inputs, enc_self_attn_mask):
'''
enc_inputs: [batch_size, src_len, d_model]
enc_self_attn_mask: [batch_size, src_len, src_len]
'''
# enc_outputs: [batch_size, src_len, d_model], attn: [batch_size, n_heads, src_len, src_len]
enc_outputs, attn = self.enc_self_attn(enc_inputs, enc_inputs, enc_inputs, enc_self_attn_mask) # enc_inputs to same Q,K,V
enc_outputs = self.pos_ffn(enc_outputs) # enc_outputs: [batch_size, src_len, d_model]
return enc_outputs, attn
Encoder
class Encoder(nn.Module):
def __init__(self):
super(Encoder, self).__init__()
self.src_emb = nn.Embedding(src_vocab_size, d_model)
self.pos_emb = PositionalEncoding(d_model)
self.layers = nn.ModuleList([EncoderLayer() for _ in range(n_layers)])
def forward(self, enc_inputs):
'''
enc_inputs: [batch_size, src_len]
'''
enc_outputs = self.src_emb(enc_inputs) # [batch_size, src_len, d_model]
enc_outputs = self.pos_emb(enc_outputs.transpose(0, 1)).transpose(0, 1) # [batch_size, src_len, d_model]
enc_self_attn_mask = get_attn_pad_mask(enc_inputs, enc_inputs) # [batch_size, src_len, src_len]
enc_self_attns = []
for layer in self.layers:
# enc_outputs: [batch_size, src_len, d_model], enc_self_attn: [batch_size, n_heads, src_len, src_len]
enc_outputs, enc_self_attn = layer(enc_outputs, enc_self_attn_mask)
enc_self_attns.append(enc_self_attn)
return enc_outputs, enc_self_attns
使用nn.ModuleList()
里面的参数是列表,列表里面存了n_layers
个 Encoder Layer
由于我们控制好了 Encoder Layer 的输入和输出维度相同,所以可以直接用个 for 循环以嵌套的方式,将上一次 Encoder Layer 的输出作为下一次 Encoder Layer 的输入
Decoder Layer
class DecoderLayer(nn.Module):
def __init__(self):
super(DecoderLayer, self).__init__()
self.dec_self_attn = MultiHeadAttention()
self.dec_enc_attn = MultiHeadAttention()
self.pos_ffn = PoswiseFeedForwardNet()
def forward(self, dec_inputs, enc_outputs, dec_self_attn_mask, dec_enc_attn_mask):
'''
dec_inputs: [batch_size, tgt_len, d_model]
enc_outputs: [batch_size, src_len, d_model]
dec_self_attn_mask: [batch_size, tgt_len, tgt_len]
dec_enc_attn_mask: [batch_size, tgt_len, src_len]
'''
# dec_outputs: [batch_size, tgt_len, d_model], dec_self_attn: [batch_size, n_heads, tgt_len, tgt_len]
dec_outputs, dec_self_attn = self.dec_self_attn(dec_inputs, dec_inputs, dec_inputs, dec_self_attn_mask)
# dec_outputs: [batch_size, tgt_len, d_model], dec_enc_attn: [batch_size, h_heads, tgt_len, src_len]
dec_outputs, dec_enc_attn = self.dec_enc_attn(dec_outputs, enc_outputs, enc_outputs, dec_enc_attn_mask)
dec_outputs = self.pos_ffn(dec_outputs) # [batch_size, tgt_len, d_model]
return dec_outputs, dec_self_attn, dec_enc_attn
在 Decoder Layer 中会调用两次 MultiHeadAttention
,第一次是计算 Decoder Input 的 self-attention,得到输出dec_outputs
。然后将 dec_outputs
作为生成 Q 的元素,enc_outputs
作为生成 K 和 V 的元素,再调用一次 MultiHeadAttention
,得到的是 Encoder 和 Decoder Layer 之间的 context vector
。最后将 dec_outptus 做一次维度变换,然后返回
Decoder
class Decoder(nn.Module):
def __init__(self):
super(Decoder, self).__init__()
self.tgt_emb = nn.Embedding(tgt_vocab_size, d_model)
self.pos_emb = PositionalEncoding(d_model)
self.layers = nn.ModuleList([DecoderLayer() for _ in range(n_layers)])
def forward(self, dec_inputs, enc_inputs, enc_outputs):
'''
dec_inputs: [batch_size, tgt_len]
enc_intpus: [batch_size, src_len]
enc_outputs: [batsh_size, src_len, d_model]
'''
dec_outputs = self.tgt_emb(dec_inputs) # [batch_size, tgt_len, d_model]
dec_outputs = self.pos_emb(dec_outputs.transpose(0, 1)).transpose(0, 1).cuda() # [batch_size, tgt_len, d_model]
dec_self_attn_pad_mask = get_attn_pad_mask(dec_inputs, dec_inputs).cuda() # [batch_size, tgt_len, tgt_len]
dec_self_attn_subsequence_mask = get_attn_subsequence_mask(dec_inputs).cuda() # [batch_size, tgt_len, tgt_len]
dec_self_attn_mask = torch.gt((dec_self_attn_pad_mask + dec_self_attn_subsequence_mask), 0).cuda() # [batch_size, tgt_len, tgt_len]
dec_enc_attn_mask = get_attn_pad_mask(dec_inputs, enc_inputs) # [batc_size, tgt_len, src_len]
dec_self_attns, dec_enc_attns = [], []
for layer in self.layers:
# dec_outputs: [batch_size, tgt_len, d_model], dec_self_attn: [batch_size, n_heads, tgt_len, tgt_len], dec_enc_attn: [batch_size, h_heads, tgt_len, src_len]
dec_outputs, dec_self_attn, dec_enc_attn = layer(dec_outputs, enc_outputs, dec_self_attn_mask, dec_enc_attn_mask)
dec_self_attns.append(dec_self_attn)
dec_enc_attns.append(dec_enc_attn)
return dec_outputs, dec_self_attns, dec_enc_attns
Decoder 中不仅要把 "pad"mask 掉,还要 mask 未来时刻的信息,因此就有了下面这三行代码,其中 torch.gt(a, value) 的意思是,将 a 中各个位置上的元素和 value 比较,若大于 value,则该位置取 1,否则取 0
dec_self_attn_pad_mask = get_attn_pad_mask(dec_inputs, dec_inputs) # [batch_size, tgt_len, tgt_len]
dec_self_attn_subsequence_mask = get_attn_subsequence_mask(dec_inputs) # [batch_size, tgt_len, tgt_len]
dec_self_attn_mask = torch.gt((dec_self_attn_pad_mask + dec_self_attn_subsequence_mask), 0) # [batch_size, tgt_len, tgt_len]
Transformer
class Transformer(nn.Module):
def __init__(self):
super(Transformer, self).__init__()
self.encoder = Encoder().cuda()
self.decoder = Decoder().cuda()
self.projection = nn.Linear(d_model, tgt_vocab_size, bias=False).cuda()
def forward(self, enc_inputs, dec_inputs):
'''
enc_inputs: [batch_size, src_len]
dec_inputs: [batch_size, tgt_len]
'''
# tensor to store decoder outputs
# outputs = torch.zeros(batch_size, tgt_len, tgt_vocab_size).to(self.device)
# enc_outputs: [batch_size, src_len, d_model], enc_self_attns: [n_layers, batch_size, n_heads, src_len, src_len]
enc_outputs, enc_self_attns = self.encoder(enc_inputs)
# dec_outpus: [batch_size, tgt_len, d_model], dec_self_attns: [n_layers, batch_size, n_heads, tgt_len, tgt_len], dec_enc_attn: [n_layers, batch_size, tgt_len, src_len]
dec_outputs, dec_self_attns, dec_enc_attns = self.decoder(dec_inputs, enc_inputs, enc_outputs)
dec_logits = self.projection(dec_outputs) # dec_logits: [batch_size, tgt_len, tgt_vocab_size]
return dec_logits.view(-1, dec_logits.size(-1)), enc_self_attns, dec_self_attns, dec_enc_attns
Transformer 主要就是调用 Encoder 和 Decoder。最后返回 dec_logits 的维度是 [batch_size * tgt_len, tgt_vocab_size]
,可以理解为,一个句子,这个句子有 batch_size*tgt_len
个单词,每个单词有 tgt_vocab_size
种情况,取概率最大者
模型 & 损失函数 & 优化器
model = Transformer().cuda()
criterion = nn.CrossEntropyLoss(ignore_index=0)
optimizer = optim.SGD(model.parameters(), lr=1e-3, momentum=0.99)
这里的损失函数里面我设置了一个参数 ignore_index=0,因为 “pad” 这个单词的索引为 0,这样设置以后,就不会计算 “pad” 的损失(因为本来 “pad” 也没有意义,不需要计算)
训练
for epoch in range(30):
for enc_inputs, dec_inputs, dec_outputs in loader:
'''
enc_inputs: [batch_size, src_len]
dec_inputs: [batch_size, tgt_len]
dec_outputs: [batch_size, tgt_len]
'''
enc_inputs, dec_inputs, dec_outputs = enc_inputs.cuda(), dec_inputs.cuda(), dec_outputs.cuda()
# outputs: [batch_size * tgt_len, tgt_vocab_size]
outputs, enc_self_attns, dec_self_attns, dec_enc_attns = model(enc_inputs, dec_inputs)
loss = criterion(outputs, dec_outputs.view(-1))
print('Epoch:', '%04d' % (epoch + 1), 'loss =', '{:.6f}'.format(loss))
optimizer.zero_grad()
loss.backward()
optimizer.step()
测试
def greedy_decoder(model, enc_input, start_symbol):
"""
For simplicity, a Greedy Decoder is Beam search when K=1. This is necessary for inference as we don't know the
target sequence input. Therefore we try to generate the target input word by word, then feed it into the transformer.
Starting Reference: http://nlp.seas.harvard.edu/2018/04/03/attention.html#greedy-decoding
:param model: Transformer Model
:param enc_input: The encoder input
:param start_symbol: The start symbol. In this example it is 'S' which corresponds to index 4
:return: The target input
"""
enc_outputs, enc_self_attns = model.encoder(enc_input)
dec_input = torch.zeros(1, tgt_len).type_as(enc_input.data)
next_symbol = start_symbol
for i in range(0, tgt_len):
dec_input[0][i] = next_symbol
dec_outputs, _, _ = model.decoder(dec_input, enc_input, enc_outputs)
projected = model.projection(dec_outputs)
prob = projected.squeeze(0).max(dim=-1, keepdim=False)[1]
next_word = prob.data[i]
next_symbol = next_word.item()
return dec_input
# Test
enc_inputs, _, _ = next(iter(loader))
greedy_dec_input = greedy_decoder(model, enc_inputs[0].view(1, -1).cuda(), start_symbol=tgt_vocab["S"])
predict, _, _, _ = model(enc_inputs[0].view(1, -1).cuda(), greedy_dec_input)
predict = predict.data.max(1, keepdim=True)[1]
print(enc_inputs[0], '->', [idx2word[n.item()] for n in predict.squeeze()])