《动手学深度学习》Task04 ：机器翻译及相关技术；注意力机制与Seq2seq模型；Transformer
Task04 ：机器翻译及相关技术；注意力机制与Seq2seq模型；Transformer
1.机器翻译及相关技术
- 机器翻译和数据集
机器翻译（MT）：将一段文本从一种语言自动翻译为另一种语言，用神经网络解决这个问题通常称为神经机器翻译（NMT）。 主要特征：输出是单词序列而不是单个单词。 输出序列的长度可能与源序列的长度不同。
步骤：
1.读取数据
2.数据预处理
3.分词：将字符串变成单词组成的列表
4.建立词典：将单词组成的列表变成单词id组成的列表
5.Encoder-Decoder：
代码实现：
num_examples = 50000
source, target = [], []
for i, line in enumerate(text.split('\n')):
if i > num_examples:
break
parts = line.split('\t')
if len(parts) >= 2:
source.append(parts[0].split(' '))
target.append(parts[1].split(' '))
source[0:3], target[0:3]
tokens = [token for line in tokens for token in line]
return d2l.data.base.Vocab(tokens, min_freq=3, use_special_tokens=True)
src_vocab = build_vocab(source)
len(src_vocab)
def pad(line, max_len, padding_token):
if len(line) > max_len:
return line[:max_len]
return line + [padding_token] * (max_len - len(line))
pad(src_vocab[source[0]], 10, src_vocab.pad)
def build_array(lines, vocab, max_len, is_source):
lines = [vocab[line] for line in lines]
if not is_source:
lines = [[vocab.bos] + line + [vocab.eos] for line in lines]
array = torch.tensor([pad(line, max_len, vocab.pad) for line in lines])
valid_len = (array != vocab.pad).sum(1) #第一个维度
return array, valid_len
class EncoderDecoder(nn.Module):
def __init__(self, encoder, decoder, **kwargs):
super(EncoderDecoder, self).__init__(**kwargs)
self.encoder = encoder
self.decoder = decoder
def forward(self, enc_X, dec_X, *args):
enc_outputs = self.encoder(enc_X, *args)
dec_state = self.decoder.init_state(enc_outputs, *args)
return self.decoder(dec_X, dec_state)
2.注意力机制与Seq2seq模型
这里Encoder的输出成为Decoder的输入
class Seq2SeqEncoder(d2l.Encoder):
def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
dropout=0, **kwargs):
super(Seq2SeqEncoder, self).__init__(**kwargs)
self.num_hiddens=num_hiddens
self.num_layers=num_layers
self.embedding = nn.Embedding(vocab_size, embed_size)
self.rnn = nn.LSTM(embed_size,num_hiddens, num_layers, dropout=dropout)
def begin_state(self, batch_size, device):
return [torch.zeros(size=(self.num_layers, batch_size, self.num_hiddens), device=device),
torch.zeros(size=(self.num_layers, batch_size, self.num_hiddens), device=device)]
def forward(self, X, *args):
X = self.embedding(X) # X shape: (batch_size, seq_len, embed_size)
X = X.transpose(0, 1) # RNN needs first axes to be time
# state = self.begin_state(X.shape[1], device=X.device)
out, state = self.rnn(X)
# The shape of out is (seq_len, batch_size, num_hiddens).
# state contains the hidden state and the memory cell
# of the last time step, the shape is (num_layers, batch_size, num_hiddens)
return out, state
class Seq2SeqDecoder(d2l.Decoder):
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.LSTM(embed_size,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):
X = self.embedding(X).transpose(0, 1)
out, state = self.rnn(X, state)
# Make the batch to be the first dimension to simplify loss computation.
out = self.dense(out).transpose(0, 1)
return out, state
def SequenceMask(X, X_len,value=0):
maxlen = X.size(1)
mask = torch.arange(maxlen)[None, :].to(X_len.device) < X_len[:, None]
X[~mask]=value
return X
class MaskedSoftmaxCELoss(nn.CrossEntropyLoss):
# pred shape: (batch_size, seq_len, vocab_size)
# label shape: (batch_size, seq_len)
# valid_length shape: (batch_size, )
def forward(self, pred, label, valid_length):
# the sample weights shape should be (batch_size, seq_len)
weights = torch.ones_like(label)
weights = SequenceMask(weights, valid_length).float()
self.reduction='none'
output=super(MaskedSoftmaxCELoss, self).forward(pred.transpose(1,2), label)
return (output*weights).mean(dim=1)
def train_ch7(model, data_iter, lr, num_epochs, device): # Saved in d2l
model.to(device)
optimizer = optim.Adam(model.parameters(), lr=lr)
loss = MaskedSoftmaxCELoss()
tic = time.time()
for epoch in range(1, num_epochs+1):
l_sum, num_tokens_sum = 0.0, 0.0
for batch in data_iter:
optimizer.zero_grad()
X, X_vlen, Y, Y_vlen = [x.to(device) for x in batch]
Y_input, Y_label, Y_vlen = Y[:,:-1], Y[:,1:], Y_vlen-1
Y_hat, _ = model(X, Y_input, X_vlen, Y_vlen)
l = loss(Y_hat, Y_label, Y_vlen).sum()
l.backward()
with torch.no_grad():
d2l.grad_clipping_nn(model, 5, device)
num_tokens = Y_vlen.sum().item()
optimizer.step()
l_sum += l.sum().item()
num_tokens_sum += num_tokens
if epoch % 50 == 0:
print("epoch {0:4d},loss {1:.3f}, time {2:.1f} sec".format(
epoch, (l_sum/num_tokens_sum), time.time()-tic))
tic = time.time()
这里简单介绍集束搜索（BeamSearch）：
我们在搜索最大可能概率单词的时候其实并不用把数据集都搜索一遍，而只是看哪些概率更大的我们搜索，所以在搜索过程中我们只需要挑出在本次搜索路线中概率最大的几个可能单词，就得到了剪枝的效果加快搜索效率.
在本图中，我们选2为集束数，AC为第一次概率较大者，第二次搜索中AB、CE为概率较大者，第三次为ABD、CED为概率较大，以此类推，得到最后的序列。
注意力机制
在“编码器—解码器（seq2seq）”⼀节⾥，解码器在各个时间步依赖相同的背景变量（context vector）来获取输⼊序列信息。当编码器为循环神经⽹络时，背景变量来⾃它最终时间步的隐藏状态。将源序列输入信息以循环单位状态编码，然后将其传递给解码器以生成目标序列。然而这种结构存在着问题，尤其是RNN机制实际中存在长程梯度消失的问题，对于较长的句子，我们很难寄希望于将输入的序列转化为定长的向量而保存所有的有效信息，所以随着所需翻译句子的长度的增加，这种结构的效果会显著下降。
与此同时，解码的目标词语可能只与原输入的部分词语有关，而并不是与所有的输入有关。例如，当把“Hello world”翻译成“Bonjour le monde”时，“Hello”映射成“Bonjour”，“world”映射成“monde”。在seq2seq模型中，解码器只能隐式地从编码器的最终状态中选择相应的信息。然而，注意力机制可以将这种选择过程显式地建模。
- 在此之前先说一下Softmax屏蔽
def SequenceMask(X, X_len,value=-1e6):
maxlen = X.size(1)
#print(X.size(),torch.arange((maxlen),dtype=torch.float)[None, :],'\n',X_len[:, None] )
mask = torch.arange((maxlen),dtype=torch.float)[None, :] >= X_len[:, None]
#print(mask)
X[mask]=value
return X
def masked_softmax(X, valid_length):
# X: 3-D tensor, valid_length: 1-D or 2-D tensor
softmax = nn.Softmax(dim=-1)
if valid_length is None:
return softmax(X)
else:
shape = X.shape
if valid_length.dim() == 1:
try:
valid_length = torch.FloatTensor(valid_length.numpy().repeat(shape[1], axis=0))#[2,2,3,3]
except:
valid_length = torch.FloatTensor(valid_length.cpu().numpy().repeat(shape[1], axis=0))#[2,2,3,3]
else:
valid_length = valid_length.reshape((-1,))
# fill masked elements with a large negative, whose exp is 0
X = SequenceMask(X.reshape((-1, shape[-1])), valid_length)
return softmax(X).reshape(shape)
- 两种注意力机制
点积注意力
class DotProductAttention(nn.Module):
def __init__(self, dropout, **kwargs):
super(DotProductAttention, self).__init__(**kwargs)
self.dropout = nn.Dropout(dropout)
# query: (batch_size, #queries, d)
# key: (batch_size, #kv_pairs, d)
# value: (batch_size, #kv_pairs, dim_v)
# valid_length: either (batch_size, ) or (batch_size, xx)
def forward(self, query, key, value, valid_length=None):
d = query.shape[-1]
# set transpose_b=True to swap the last two dimensions of key
scores = torch.bmm(query, key.transpose(1,2)) / math.sqrt(d)
attention_weights = self.dropout(masked_softmax(scores, valid_length))
print("attention_weight\n",attention_weights)
return torch.bmm(attention_weights, value)
atten = DotProductAttention(dropout=0)
keys = torch.ones((2,10,2),dtype=torch.float)
values = torch.arange((40), dtype=torch.float).view(1,10,4).repeat(2,1,1)
atten(torch.ones((2,1,2),dtype=torch.float), keys, values, torch.FloatTensor([2, 6]))
attention_weight
tensor([[[0.5000, 0.5000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000, 0.0000,
0.0000, 0.0000]],
[[0.1667, 0.1667, 0.1667, 0.1667, 0.1667, 0.1667, 0.0000, 0.0000,
0.0000, 0.0000]]])
- 多层感知机注意力
class MLPAttention(nn.Module):
def __init__(self, units,ipt_dim,dropout, **kwargs):
super(MLPAttention, self).__init__(**kwargs)
# Use flatten=True to keep query's and key's 3-D shapes.
self.W_k = nn.Linear(ipt_dim, units, bias=False)
self.W_q = nn.Linear(ipt_dim, units, bias=False)
self.v = nn.Linear(units, 1, bias=False)
self.dropout = nn.Dropout(dropout)
def forward(self, query, key, value, valid_length):
query, key = self.W_k(query), self.W_q(key)
#print("size",query.size(),key.size())
# expand query to (batch_size, #querys, 1, units), and key to
# (batch_size, 1, #kv_pairs, units). Then plus them with broadcast.
features = query.unsqueeze(2) + key.unsqueeze(1)
#print("features:",features.size()) #--------------开启
scores = self.v(features).squeeze(-1)
attention_weights = self.dropout(masked_softmax(scores, valid_length))
return torch.bmm(attention_weights, value)
atten = MLPAttention(ipt_dim=2,units = 8, dropout=0)
atten(torch.ones((2,1,2), dtype = torch.float), keys, values, torch.FloatTensor([2, 6]))
- 引入注意力机制的Seq2seq模型
本节中将注意机制添加到sequence to sequence 模型中，以显式地使用权重聚合states。下图展示encoding 和decoding的模型结构，在时间步为t的时候。此刻attention layer保存着encodering看到的所有信息——即encoding的每一步输出。在decoding阶段，解码器的时刻的隐藏状态被当作query，encoder的每个时间步的hidden states作为key和value进行attention聚合. Attetion model的输出当作成上下文信息context vector，并与解码器输入Dt拼接起来一起送到解码器：
- 解码器
由于带有注意机制的seq2seq的编码器与之前章节中的Seq2SeqEncoder相同，所以在此处我们只关注解码器。我们添加了一个MLP注意层(MLPAttention)，它的隐藏大小与解码器中的LSTM层相同。然后我们通过从编码器传递三个参数来初始化解码器的状态:
- the encoder outputs of all timesteps：encoder输出的各个状态，被用于attetion layer的memory部分，有相同的key和values
- the hidden state of the encoder’s final timestep：编码器最后一个时间步的隐藏状态，被用于初始化decoder 的hidden state
- the encoder valid length: 编码器的有效长度，借此，注意层不会考虑编码器输出中的填充标记（Paddings）
在解码的每个时间步，我们使用解码器的最后一个RNN层的输出作为注意层的query。然后，将注意力模型的输出与输入嵌入向量连接起来，输入到RNN层。虽然RNN层隐藏状态也包含来自解码器的历史信息，但是attention model的输出显式地选择了enc_valid_len以内的编码器输出，这样attention机制就会尽可能排除其他不相关的信息。
class Seq2SeqAttentionDecoder(d2l.Decoder):
def __init__(self, vocab_size, embed_size, num_hiddens, num_layers,
dropout=0, **kwargs):
super(Seq2SeqAttentionDecoder, self).__init__(**kwargs)
self.attention_cell = MLPAttention(num_hiddens,num_hiddens, dropout)
self.embedding = nn.Embedding(vocab_size, embed_size)
self.rnn = nn.LSTM(embed_size+ num_hiddens,num_hiddens, num_layers, dropout=dropout)
self.dense = nn.Linear(num_hiddens,vocab_size)
def init_state(self, enc_outputs, enc_valid_len, *args):
outputs, hidden_state = enc_outputs
# print("first:",outputs.size(),hidden_state[0].size(),hidden_state[1].size())
# Transpose outputs to (batch_size, seq_len, hidden_size)
return (outputs.permute(1,0,-1), hidden_state, enc_valid_len)
#outputs.swapaxes(0, 1)
def forward(self, X, state):
enc_outputs, hidden_state, enc_valid_len = state
#("X.size",X.size())
X = self.embedding(X).transpose(0,1)
# print("Xembeding.size2",X.size())
outputs = []
for l, x in enumerate(X):
# print(f"\n{l}-th token")
# print("x.first.size()",x.size())
# query shape: (batch_size, 1, hidden_size)
# select hidden state of the last rnn layer as query
query = hidden_state[0][-1].unsqueeze(1) # np.expand_dims(hidden_state[0][-1], axis=1)
# context has same shape as query
# print("query enc_outputs, enc_outputs:\n",query.size(), enc_outputs.size(), enc_outputs.size())
context = self.attention_cell(query, enc_outputs, enc_outputs, enc_valid_len)
# Concatenate on the feature dimension
# print("context.size:",context.size())
x = torch.cat((context, x.unsqueeze(1)), dim=-1)
# Reshape x to (1, batch_size, embed_size+hidden_size)
# print("rnn",x.size(), len(hidden_state))
out, hidden_state = self.rnn(x.transpose(0,1), hidden_state)
outputs.append(out)
outputs = self.dense(torch.cat(outputs, dim=0))
return outputs.transpose(0, 1), [enc_outputs, hidden_state,
enc_valid_len]
encoder = d2l.Seq2SeqEncoder(vocab_size=10, embed_size=8,
num_hiddens=16, num_layers=2)
# encoder.initialize()
decoder = Seq2SeqAttentionDecoder(vocab_size=10, embed_size=8,
num_hiddens=16, num_layers=2)
X = torch.zeros((4, 7),dtype=torch.long)
print("batch size=4\nseq_length=7\nhidden dim=16\nnum_layers=2\n")
print('encoder output size:', encoder(X)[0].size())
print('encoder hidden size:', encoder(X)[1][0].size())
print('encoder memory size:', encoder(X)[1][1].size())
state = decoder.init_state(encoder(X), None)
out, state = decoder(X, state)
out.shape, len(state), state[0].shape, len(state[1]), state[1][0].shape
3.Transformer
在之前的章节中，我们已经介绍了主流的神经网络架构如卷积神经网络（CNNs）和循环神经网络（RNNs）。让我们进行一些回顾：
- CNNs 易于并行化，却不适合捕捉变长序列内的依赖关系。
- RNNs 适合捕捉长距离变长序列的依赖，但是却难以实现并行化处理序列。
为了整合CNN和RNN的优势，[Vaswani et al., 2017] 创新性地使用注意力机制设计了Transformer模型。该模型利用attention机制实现了并行化捕捉序列依赖，并且同时处理序列的每个位置的tokens，上述优势使得Transformer模型在性能优异的同时大大减少了训练时间。
图10.3.1展示了Transformer模型的架构，与9.7节的seq2seq模型相似，Transformer同样基于编码器-解码器架构，其区别主要在于以下三点：
1.Transformer blocks：将seq2seq模型重的循环网络替换为了Transformer Blocks，该模块包含一个多头注意力层（Multi-head Attention Layers）以及两个position-wise feed-forward networks（FFN）。对于解码器来说，另一个多头注意力层被用于接受编码器的隐藏状态。
2.Add and norm：多头注意力层和前馈网络的输出被送到两个“add and norm”层进行处理，该层包含残差结构以及层归一化。
3.Position encoding：由于自注意力层并没有区分元素的顺序，所以一个位置编码层被用于向序列元素里添加位置信息。
- 多头注意力层
在我们讨论多头注意力层之前，先来迅速理解以下自注意力（self-attention）的结构。自注意力模型是一个正规的注意力模型，序列的每一个元素对应的key，value，query是完全一致的。如图10.3.2 自注意力输出了一个与输入长度相同的表征序列，与循环神经网络相比，自注意力对每个元素输出的计算是并行的，所以我们可以高效的实现这个模块。
多头注意力层包含h个并行的自注意力层，每一个这种层被成为一个head。对每个头来说，在进行注意力计算之前，我们会将query、key和value用三个现行层进行映射，这h个注意力头的输出将会被拼接之后输入最后一个线性层进行整合。
class MultiHeadAttention(nn.Module):
def __init__(self, input_size, hidden_size, num_heads, dropout, **kwargs):
super(MultiHeadAttention, self).__init__(**kwargs)
self.num_heads = num_heads
self.attention = DotProductAttention(dropout)
self.W_q = nn.Linear(input_size, hidden_size, bias=False)
self.W_k = nn.Linear(input_size, hidden_size, bias=False)
self.W_v = nn.Linear(input_size, hidden_size, bias=False)
self.W_o = nn.Linear(hidden_size, hidden_size, bias=False)
def forward(self, query, key, value, valid_length):
# query, key, and value shape: (batch_size, seq_len, dim),
# where seq_len is the length of input sequence
# valid_length shape is either (batch_size, )
# or (batch_size, seq_len).
# Project and transpose query, key, and value from
# (batch_size, seq_len, hidden_size * num_heads) to
# (batch_size * num_heads, seq_len, hidden_size).
query = transpose_qkv(self.W_q(query), self.num_heads)
key = transpose_qkv(self.W_k(key), self.num_heads)
value = transpose_qkv(self.W_v(value), self.num_heads)
if valid_length is not None:
# Copy valid_length by num_heads times
device = valid_length.device
valid_length = valid_length.cpu().numpy() if valid_length.is_cuda else valid_length.numpy()
if valid_length.ndim == 1:
valid_length = torch.FloatTensor(np.tile(valid_length, self.num_heads))
else:
valid_length = torch.FloatTensor(np.tile(valid_length, (self.num_heads,1)))
valid_length = valid_length.to(device)
output = self.attention(query, key, value, valid_length)
output_concat = transpose_output(output, self.num_heads)
return self.W_o(output_concat)
def transpose_qkv(X, num_heads):
# Original X shape: (batch_size, seq_len, hidden_size * num_heads),
# -1 means inferring its value, after first reshape, X shape:
# (batch_size, seq_len, num_heads, hidden_size)
X = X.view(X.shape[0], X.shape[1], num_heads, -1)
# After transpose, X shape: (batch_size, num_heads, seq_len, hidden_size)
X = X.transpose(2, 1).contiguous()
# Merge the first two dimensions. Use reverse=True to infer shape from
# right to left.
# output shape: (batch_size * num_heads, seq_len, hidden_size)
output = X.view(-1, X.shape[2], X.shape[3])
return output
# Saved in the d2l package for later use
def transpose_output(X, num_heads):
# A reversed version of transpose_qkv
X = X.view(-1, num_heads, X.shape[1], X.shape[2])
X = X.transpose(2, 1).contiguous()
return X.view(X.shape[0], X.shape[1], -1)
cell = MultiHeadAttention(5, 9, 3, 0.5)
X = torch.ones((2, 4, 5))
valid_length = torch.FloatTensor([2, 3])
cell(X, X, X, valid_length).shape
- 基于位置的前馈网络
Transformer 模块另一个非常重要的部分就是基于位置的前馈网络（FFN），它接受一个形状为（batch_size，seq_length, feature_size）的三维张量。Position-wise FFN由两个全连接层组成，他们作用在最后一维上。因为序列的每个位置的状态都会被单独地更新，所以我们称他为position-wise，这等效于一个1x1的卷积。
class PositionWiseFFN(nn.Module):
def __init__(self, input_size, ffn_hidden_size, hidden_size_out, **kwargs):
super(PositionWiseFFN, self).__init__(**kwargs)
self.ffn_1 = nn.Linear(input_size, ffn_hidden_size)
self.ffn_2 = nn.Linear(ffn_hidden_size, hidden_size_out)
def forward(self, X):
return self.ffn_2(F.relu(self.ffn_1(X)))
与多头注意力层相似，FFN层同样只会对最后一维的大小进行改变；除此之外，对于两个完全相同的输入，FFN层的输出也将相等。
- Add and Norm
除了上面两个模块之外，Transformer还有一个重要的相加归一化层，它可以平滑地整合输入和其他层的输出，因此我们在每个多头注意力层和FFN层后面都添加一个含残差连接的Layer Norm层。这里 Layer Norm 与7.5小节的Batch Norm很相似，唯一的区别在于Batch Norm是对于batch size这个维度进行计算均值和方差的，而Layer Norm则是对最后一维进行计算。层归一化可以防止层内的数值变化过大，从而有利于加快训练速度并且提高泛化性能。
layernorm = nn.LayerNorm(normalized_shape=2, elementwise_affine=True)
batchnorm = nn.BatchNorm1d(num_features=2, affine=True)
X = torch.FloatTensor([[1,2], [3,4]])
print('layer norm:', layernorm(X))
print('batch norm:', batchnorm(X))
class AddNorm(nn.Module):
def __init__(self, hidden_size, dropout, **kwargs):
super(AddNorm, self).__init__(**kwargs)
self.dropout = nn.Dropout(dropout)
self.norm = nn.LayerNorm(hidden_size)
def forward(self, X, Y):
return self.norm(self.dropout(Y) + X)
add_norm = AddNorm(4, 0.5)
add_norm(torch.ones((2,3,4)), torch.ones((2,3,4))).shape
- 位置编码
class PositionalEncoding(nn.Module):
def __init__(self, embedding_size, dropout, max_len=1000):
super(PositionalEncoding, self).__init__()
self.dropout = nn.Dropout(dropout)
self.P = np.zeros((1, max_len, embedding_size))
X = np.arange(0, max_len).reshape(-1, 1) / np.power(
10000, np.arange(0, embedding_size, 2)/embedding_size)
self.P[:, :, 0::2] = np.sin(X)
self.P[:, :, 1::2] = np.cos(X)
self.P = torch.FloatTensor(self.P)
def forward(self, X):
if X.is_cuda and not self.P.is_cuda:
self.P = self.P.cuda()
X = X + self.P[:, :X.shape[1], :]
return self.dropout(X)
这使得不同序列的信息的相位不同，例如：
- 编码器
我们已经有了组成Transformer的各个模块，现在我们可以开始搭建了！编码器包含一个多头注意力层，一个position-wise FFN，和两个 Add and Norm层。对于attention模型以及FFN模型，我们的输出维度都是与embedding维度一致的，这也是由于残差连接天生的特性导致的，因为我们要将前一层的输出与原始输入相加并归一化。
class EncoderBlock(nn.Module):
def __init__(self, embedding_size, ffn_hidden_size, num_heads,
dropout, **kwargs):
super(EncoderBlock, self).__init__(**kwargs)
self.attention = MultiHeadAttention(embedding_size, embedding_size, num_heads, dropout)
self.addnorm_1 = AddNorm(embedding_size, dropout)
self.ffn = PositionWiseFFN(embedding_size, ffn_hidden_size, embedding_size)
self.addnorm_2 = AddNorm(embedding_size, dropout)
def forward(self, X, valid_length):
Y = self.addnorm_1(X, self.attention(X, X, X, valid_length))
return self.addnorm_2(Y, self.ffn(Y))
X = torch.ones((2, 100, 24))
encoder_blk = EncoderBlock(24, 48, 8, 0.5)
encoder_blk(X, valid_length).shape
实现整个Transformer 编码器模型，整个编码器由n个刚刚定义的Encoder Block堆叠而成，因为残差连接的缘故，中间状态的维度始终与嵌入向量的维度d一致；同时注意到我们把嵌入向量乘以 d^(1/2)以防止其值过小。
class TransformerEncoder(d2l.Encoder):
def __init__(self, vocab_size, embedding_size, ffn_hidden_size,
num_heads, num_layers, dropout, **kwargs):
super(TransformerEncoder, self).__init__(**kwargs)
self.embedding_size = embedding_size
self.embed = nn.Embedding(vocab_size, embedding_size)
self.pos_encoding = PositionalEncoding(embedding_size, dropout)
self.blks = nn.ModuleList()
for i in range(num_layers):
self.blks.append(
EncoderBlock(embedding_size, ffn_hidden_size,
num_heads, dropout))
def forward(self, X, valid_length, *args):
X = self.pos_encoding(self.embed(X) * math.sqrt(self.embedding_size))
for blk in self.blks:
X = blk(X, valid_length)
return X
encoder = TransformerEncoder(200, 24, 48, 8, 2, 0.5)
encoder(torch.ones((2, 100)).long(), valid_length).shape
解码器
def __init__(self, embedding_size, ffn_hidden_size, num_heads,dropout,i,**kwargs):
super(DecoderBlock, self).__init__(**kwargs)
self.i = i
self.attention_1 = MultiHeadAttention(embedding_size, embedding_size, num_heads, dropout)
self.addnorm_1 = AddNorm(embedding_size, dropout)
self.attention_2 = MultiHeadAttention(embedding_size, embedding_size, num_heads, dropout)
self.addnorm_2 = AddNorm(embedding_size, dropout)
self.ffn = PositionWiseFFN(embedding_size, ffn_hidden_size, embedding_size)
self.addnorm_3 = AddNorm(embedding_size, dropout)
def forward(self, X, state):
enc_outputs, enc_valid_length = state[0], state[1]
# state[2][self.i] stores all the previous t-1 query state of layer-i
# len(state[2]) = num_layers
# If training:
# state[2] is useless.
# If predicting:
# In the t-th timestep:
# state[2][self.i].shape = (batch_size, t-1, hidden_size)
# Demo:
# love dogs ! [EOS]
# | | | |
# Transformer
# Decoder
# | | | |
# I love dogs !
if state[2][self.i] is None:
key_values = X
else:
# shape of key_values = (batch_size, t, hidden_size)
key_values = torch.cat((state[2][self.i], X), dim=1)
state[2][self.i] = key_values
if self.training:
batch_size, seq_len, _ = X.shape
# Shape: (batch_size, seq_len), the values in the j-th column are j+1
valid_length = torch.FloatTensor(np.tile(np.arange(1, seq_len+1), (batch_size, 1)))
valid_length = valid_length.to(X.device)
else:
valid_length = None
X2 = self.attention_1(X, key_values, key_values, valid_length)
Y = self.addnorm_1(X, X2)
Y2 = self.attention_2(Y, enc_outputs, enc_outputs, enc_valid_length)
Z = self.addnorm_2(Y, Y2)
return self.addnorm_3(Z, self.ffn(Z)), state
class TransformerDecoder(d2l.Decoder):
def __init__(self, vocab_size, embedding_size, ffn_hidden_size,
num_heads, num_layers, dropout, **kwargs):
super(TransformerDecoder, self).__init__(**kwargs)
self.embedding_size = embedding_size
self.num_layers = num_layers
self.embed = nn.Embedding(vocab_size, embedding_size)
self.pos_encoding = PositionalEncoding(embedding_size, dropout)
self.blks = nn.ModuleList()
for i in range(num_layers):
self.blks.append(
DecoderBlock(embedding_size, ffn_hidden_size, num_heads,
dropout, i))
self.dense = nn.Linear(embedding_size, vocab_size)
def init_state(self, enc_outputs, enc_valid_length, *args):
return [enc_outputs, enc_valid_length, [None]*self.num_layers]
def forward(self, X, state):
X = self.pos_encoding(self.embed(X) * math.sqrt(self.embedding_size))
for blk in self.blks:
X, state = blk(X, state)
return self.dense(X), state
参考资料：
https://www.kesci.com/org/boyuai/project/5e43f70f5f2816002ceb6357
https://www.kesci.com/org/boyuai/project/5e43cb9a5f2816002ceadf6d
https://www.kesci.com/org/boyuai/project/5e43cba95f2816002ceadfab