Transformer的PyTorch实现

2020-07-15 10:14:15 浏览数 (1)

文本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

代码语言:javascript复制
# 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

下面变量代表的含义依次是

  1. 字嵌入&位置嵌入的维度,这俩值是相同的,因此用一个变量就行了
  2. FeedForward层隐藏神经元个数
  3. Q、K、V向量的维度,其中Q与K的维度必须相等,V的维度没有限制,不过为了方便起见,我都设为64
  4. Encoder和Decoder的个数
  5. 多头注意力中head的数量
代码语言:javascript复制
# 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

关于代码中的注释,如果值为src_len或者tgt_len的,我一定会写清楚,但是有些函数或者类,Encoder和Decoder都有可能调用,因此就不能确定究竟是src_len还是tgt_len,对于不确定的,我会记作seq_len

Positional Encoding

代码语言:javascript复制
def get_sinusoid_encoding_table(n_position, d_model):
    def cal_angle(position, hid_idx):
        return position / np.power(10000, 2 * (hid_idx // 2) / d_model)
    def get_posi_angle_vec(position):
        return [cal_angle(position, hid_j) for hid_j in range(d_model)]

    sinusoid_table = np.array([get_posi_angle_vec(pos_i) for pos_i in range(n_position)])
    sinusoid_table[:, 0::2] = np.sin(sinusoid_table[:, 0::2])  # dim 2i
    sinusoid_table[:, 1::2] = np.cos(sinusoid_table[:, 1::2])  # dim 2i 1
    return torch.FloatTensor(sinusoid_table)

这段代码并不复杂,传入的参数分别是字库的大小,以及位置编码的维度。最终返回的参数,维度也即[n_position, d_model],和字编码的大小一摸一样

Pad Mask

代码语言:javascript复制
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]

由于在Encoder和Decoder中都需要进行mask操作,因此就无法确定这个函数的参数中seq_len的值,如果是在Encoder中调用的,seq_len就等于src_len;如果是在Decoder中调用的,seq_len就有可能等于src_len,也有可能等于tgt_len(因为Decoder有两次mask)

这个函数最核心的一句代码是seq_k.data.eq(0),这句的作用是返回一个大小和seq_k一样的tensor,只不过里面的值只有True和False。如果seq_k某个位置的值等于0,那么对应位置就是True,否则即为False。举个例子,输入为seq_data = [1, 2, 3, 4, 0]seq_data.data.eq(0)就会返回[False, False, False, False, True]

剩下的代码主要是扩展维度,强烈建议读者打印出来,看看最终返回的数据是什么样子

Subsequence Mask

代码语言:javascript复制
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

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,下图是np.triu()用法

ScaledDotProductAttention

代码语言:javascript复制
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QK计算出scores,然后将scoresV相乘,得到每个单词的context vector

第一步是将QK的转置相乘没什么好说的,相乘之后得到的scores还不能立刻进行softmax,需要和attn_mask相加,把一些需要屏蔽的信息屏蔽掉,attn_mask是一个仅由True和False组成的tensor,并且一定会保证attn_maskscores的维度四个值相同(不然无法做对应位置相加)

mask完了之后,就可以对scores进行softmax了。然后再与V相乘,得到context

MultiHeadAttention

代码语言:javascript复制
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)(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_Qinput_Kinput_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_outputsenc_outputsenc_outputs

FeedForward Layer

代码语言:javascript复制
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)(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

代码语言:javascript复制
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

将上述组件拼起来,就是一个完整的Encoder Layer

Encoder

代码语言:javascript复制
class Encoder(nn.Module):
    def __init__(self):
        super(Encoder, self).__init__()
        self.src_emb = nn.Embedding(src_vocab_size, d_model)
        self.pos_emb = nn.Embedding.from_pretrained(get_sinusoid_encoding_table(src_vocab_size, d_model),freeze=True)
        self.layers = nn.ModuleList([EncoderLayer() for _ in range(n_layers)])

    def forward(self, enc_inputs):
        '''
        enc_inputs: [batch_size, src_len]
        '''
        word_emb = self.src_emb(enc_inputs) # [batch_size, src_len, d_model]
        pos_emb = self.pos_emb(enc_inputs) # [batch_size, src_len, d_model]
        enc_outputs = word_emb   pos_emb
        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

代码语言:javascript复制
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

代码语言:javascript复制
class Decoder(nn.Module):
    def __init__(self):
        super(Decoder, self).__init__()
        self.tgt_emb = nn.Embedding(tgt_vocab_size, d_model)
        self.pos_emb = nn.Embedding.from_pretrained(get_sinusoid_encoding_table(tgt_vocab_size, d_model),freeze=True)
        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]
        '''
        word_emb = self.tgt_emb(dec_inputs) # [batch_size, tgt_len, d_model]
        pos_emb = self.pos_emb(dec_inputs) # [batch_size, tgt_len, d_model]
        dec_outputs = word_emb   pos_emb
        dec_self_attn_pad_mask = get_attn_pad_mask(dec_inputs, dec_inputs) # [batch_size, tgt_len, tgt_len]
        dec_self_attn_subsequent_mask = get_attn_subsequence_mask(dec_inputs) # [batch_size, tgt_len]
        dec_self_attn_mask = torch.gt((dec_self_attn_pad_mask   dec_self_attn_subsequent_mask), 0) # [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

代码语言:javascript复制
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

代码语言:javascript复制
class Transformer(nn.Module):
    def __init__(self):
        super(Transformer, self).__init__()
        self.encoder = Encoder()
        self.decoder = Decoder()
        self.projection = nn.Linear(d_model, tgt_vocab_size, bias=False)
    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

代码语言:javascript复制
model = Transformer()
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),关于这个参数更详细的说明,可以看我这篇文章的最下面,稍微提了一下

训练

代码语言:javascript复制
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.to(device), dec_inputs.to(device), dec_outputs.to(device)
      # 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:', 'd' % (epoch   1), 'loss =', '{:.6f}'.format(loss))

      optimizer.zero_grad()
      loss.backward()
      optimizer.step()

测试

代码语言:javascript复制
enc_inputs, dec_inputs, _ = next(iter(loader))
predict, _, _, _ = model(enc_inputs[0].view(1, -1), dec_inputs[0].view(1, -1)) # model(enc_inputs[0].view(1, -1), greedy_dec_input)
predict = predict.data.max(1, keepdim=True)[1]
print(enc_inputs[0], '->', [idx2word[n.item()] for n in predict.squeeze()])

0 人点赞