代码来源：https://github.com/graykode/nlp-tutorial/blob/master/5-1.Transformer/Transformer-Torch.py
一些基础变量和参数：
import numpy as np import torch import torch.nn as nn import torch.optim as optim from torch.autograd import Variable import matplotlib.pyplot as plt dtype = torch.FloatTensor # 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 = ['ich mochte ein bier P', 'S i want a beer', 'i want a beer E'] # Transformer Parameters # Padding Should be Zero src_vocab = {'P' : 0, 'ich' : 1, 'mochte' : 2, 'ein' : 3, 'bier' : 4} src_vocab_size = len(src_vocab) tgt_vocab = {'P' : 0, 'i' : 1, 'want' : 2, 'a' : 3, 'beer' : 4, 'S' : 5, 'E' : 6} number_dict = {i: w for i, w in enumerate(tgt_vocab)} tgt_vocab_size = len(tgt_vocab) src_len = 5 tgt_len = 5 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
函数一：将句子转换成向量
def make_batch(sentences): input_batch = [[src_vocab[n] for n in sentences[0].split()]] output_batch = [[tgt_vocab[n] for n in sentences[1].split()]] target_batch = [[tgt_vocab[n] for n in sentences[2].split()]] return Variable(torch.LongTensor(input_batch)), Variable(torch.LongTensor(output_batch)), Variable(torch.LongTensor(target_batch))
input_batch,output_batch,target_batch=make_batch(sentences)
input_batch,output_batch,target_batch
输出：
(tensor([[1, 2, 3, 4, 0]]), tensor([[5, 1, 2, 3, 4]]), tensor([[1, 2, 3, 4, 6]]))
函数二：位置嵌入
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)
sinusoid_table=get_sinusoid_encoding_table(src_len+1,d_model)
sinusoid_table.shape
torch.Size([6, 512])
sinusoid_table
tensor([[ 0.0000e+00, 1.0000e+00, 0.0000e+00, ..., 1.0000e+00, 0.0000e+00, 1.0000e+00], [ 8.4147e-01, 5.4030e-01, 8.2186e-01, ..., 1.0000e+00, 1.0366e-04, 1.0000e+00], [ 9.0930e-01, -4.1615e-01, 9.3641e-01, ..., 1.0000e+00, 2.0733e-04, 1.0000e+00], [ 1.4112e-01, -9.8999e-01, 2.4509e-01, ..., 1.0000e+00, 3.1099e-04, 1.0000e+00], [-7.5680e-01, -6.5364e-01, -6.5717e-01, ..., 1.0000e+00, 4.1465e-04, 1.0000e+00], [-9.5892e-01, 2.8366e-01, -9.9385e-01, ..., 1.0000e+00, 5.1832e-04, 1.0000e+00]])
函数三：mask机制
def get_attn_pad_mask(seq_q, seq_k): 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 x 1 x len_k(=len_q), one is masking return pad_attn_mask.expand(batch_size, len_q, len_k) # batch_size x len_q x len_k
函数四：
def get_attn_subsequent_mask(seq): attn_shape = [seq.size(0), seq.size(1), seq.size(1)] subsequent_mask = np.triu(np.ones(attn_shape), k=1) subsequent_mask = torch.from_numpy(subsequent_mask).byte() return subsequent_mask
不同的层：
class ScaledDotProductAttention(nn.Module): def __init__(self): super(ScaledDotProductAttention, self).__init__() def forward(self, Q, K, V, attn_mask): scores = torch.matmul(Q, K.transpose(-1, -2)) / np.sqrt(d_k) # scores : [batch_size x n_heads x len_q(=len_k) x len_k(=len_q)] scores.masked_fill_(attn_mask, -1e9) # Fills elements of self tensor with value where mask is one. attn = nn.Softmax(dim=-1)(scores) context = torch.matmul(attn, V) return context, attn class MultiHeadAttention(nn.Module): def __init__(self): super(MultiHeadAttention, self).__init__() self.W_Q = nn.Linear(d_model, d_k * n_heads) self.W_K = nn.Linear(d_model, d_k * n_heads) self.W_V = nn.Linear(d_model, d_v * n_heads) def forward(self, Q, K, V, attn_mask): # q: [batch_size x len_q x d_model], k: [batch_size x len_k x d_model], v: [batch_size x len_k x d_model] residual, batch_size = Q, Q.size(0) # (B, S, D) -proj-> (B, S, D) -split-> (B, S, H, W) -trans-> (B, H, S, W) q_s = self.W_Q(Q).view(batch_size, -1, n_heads, d_k).transpose(1,2) # q_s: [batch_size x n_heads x len_q x d_k] k_s = self.W_K(K).view(batch_size, -1, n_heads, d_k).transpose(1,2) # k_s: [batch_size x n_heads x len_k x d_k] v_s = self.W_V(V).view(batch_size, -1, n_heads, d_v).transpose(1,2) # v_s: [batch_size x n_heads x len_k x d_v] attn_mask = attn_mask.unsqueeze(1).repeat(1, n_heads, 1, 1) # attn_mask : [batch_size x n_heads x len_q x len_k] # context: [batch_size x n_heads x len_q x d_v], attn: [batch_size x n_heads x len_q(=len_k) x len_k(=len_q)] context, attn = ScaledDotProductAttention()(q_s, k_s, v_s, attn_mask) context = context.transpose(1, 2).contiguous().view(batch_size, -1, n_heads * d_v) # context: [batch_size x len_q x n_heads * d_v] output = nn.Linear(n_heads * d_v, d_model)(context) return nn.LayerNorm(d_model)(output + residual), attn # output: [batch_size x len_q x d_model] class PoswiseFeedForwardNet(nn.Module): def __init__(self): super(PoswiseFeedForwardNet, self).__init__() self.conv1 = nn.Conv1d(in_channels=d_model, out_channels=d_ff, kernel_size=1) self.conv2 = nn.Conv1d(in_channels=d_ff, out_channels=d_model, kernel_size=1) def forward(self, inputs): residual = inputs # inputs : [batch_size, len_q, d_model] output = nn.ReLU()(self.conv1(inputs.transpose(1, 2))) output = self.conv2(output).transpose(1, 2) return nn.LayerNorm(d_model)(output + residual) 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_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 x len_q x d_model] return enc_outputs, attn 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_outputs, dec_self_attn = self.dec_self_attn(dec_inputs, dec_inputs, dec_inputs, dec_self_attn_mask) 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) return dec_outputs, dec_self_attn, dec_enc_attn 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_len+1, d_model),freeze=True) self.layers = nn.ModuleList([EncoderLayer() for _ in range(n_layers)]) def forward(self, enc_inputs): # enc_inputs : [batch_size x source_len] enc_outputs = self.src_emb(enc_inputs) + self.pos_emb(torch.LongTensor([[1,2,3,4,0]])) enc_self_attn_mask = get_attn_pad_mask(enc_inputs, enc_inputs) enc_self_attns = [] for layer in self.layers: 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 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_len+1, 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 x target_len] dec_outputs = self.tgt_emb(dec_inputs) + self.pos_emb(torch.LongTensor([[5,1,2,3,4]])) dec_self_attn_pad_mask = get_attn_pad_mask(dec_inputs, dec_inputs) dec_self_attn_subsequent_mask = get_attn_subsequent_mask(dec_inputs) dec_self_attn_mask = torch.gt((dec_self_attn_pad_mask + dec_self_attn_subsequent_mask), 0) dec_enc_attn_mask = get_attn_pad_mask(dec_inputs, enc_inputs) dec_self_attns, dec_enc_attns = [], [] for layer in self.layers: 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 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_outputs, enc_self_attns = self.encoder(enc_inputs) 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 x src_vocab_size x tgt_vocab_size] return dec_logits.view(-1, dec_logits.size(-1)), enc_self_attns, dec_self_attns, dec_enc_attns
从Transformer类中慢慢看过来：
model = Transformer()
初始化的时候：构建编码器、解码器、前馈神经网络。
在前向传播的过程中：
编码器输入(源语言)--》编码器输出、编码器自注意力
解码器输入(目标语言、源语言、编码器输出)--》解码器输出、解码器自注意力、解码-编码注意力
前馈神经网络输入(解码器输出)--》dec_logits
分别打印一下每个变量的形状：
model=Transformer() enc_inputs, dec_inputs, target_batch = make_batch(sentences) outputs, enc_self_attns, dec_self_attns, dec_enc_attns = model(enc_inputs, dec_inputs)
enc_inputs的形状是： torch.Size([1, 5]) enc_inputs的形状是： torch.Size([1, 5]) enc_outputs的形状是： torch.Size([1, 5, 512]) enc_self_attns的形状是： (6,) dec_outputs的形状是： torch.Size([1, 5, 512]) dec_self_attns的形状是： (6,) dec_enc_attns的形状是： (6,)
其中的细节再看了。
最后是训练和预测：
model = Transformer() criterion = nn.CrossEntropyLoss() optimizer = optim.Adam(model.parameters(), lr=0.001) def showgraph(attn): attn = attn[-1].squeeze(0)[0] attn = attn.squeeze(0).data.numpy() fig = plt.figure(figsize=(n_heads, n_heads)) # [n_heads, n_heads] ax = fig.add_subplot(1, 1, 1) ax.matshow(attn, cmap='viridis') ax.set_xticklabels(['']+sentences[0].split(), fontdict={'fontsize': 14}, rotation=90) ax.set_yticklabels(['']+sentences[2].split(), fontdict={'fontsize': 14}) plt.show() for epoch in range(20): optimizer.zero_grad() enc_inputs, dec_inputs, target_batch = make_batch(sentences) outputs, enc_self_attns, dec_self_attns, dec_enc_attns = model(enc_inputs, dec_inputs) loss = criterion(outputs, target_batch.contiguous().view(-1)) print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.6f}'.format(loss)) loss.backward() optimizer.step() # Test predict, _, _, _ = model(enc_inputs, dec_inputs) predict = predict.data.max(1, keepdim=True)[1] print(sentences[0], '->', [number_dict[n.item()] for n in predict.squeeze()]) print('first head of last state enc_self_attns') showgraph(enc_self_attns) print('first head of last state dec_self_attns') showgraph(dec_self_attns) print('first head of last state dec_enc_attns') showgraph(dec_enc_attns)
结果：
