1. Transformer
2. 多头注意力代码
通过不断地reshape,避免forloop操作。
什么样的shape进去,怎样的shape出来。
#@save
class MultiHeadAttention(nn.Module):"""多头注意力"""def __init__(self, key_size, query_size, value_size, num_hiddens,num_heads, dropout, bias=False, **kwargs):super(MultiHeadAttention, self).__init__(**kwargs)self.num_heads = num_headsself.attention = d2l.DotProductAttention(dropout)self.W_q = nn.Linear(query_size, num_hiddens, bias=bias)self.W_k = nn.Linear(key_size, num_hiddens, bias=bias)self.W_v = nn.Linear(value_size, num_hiddens, bias=bias)self.W_o = nn.Linear(num_hiddens, num_hiddens, bias=bias)def forward(self, queries, keys, values, valid_lens):# queries,keys,values的形状:# (batch_size,查询或者“键-值”对的个数,num_hiddens)# valid_lens 的形状:# (batch_size,)或(batch_size,查询的个数)# 经过变换后,输出的queries,keys,values 的形状:# (batch_size*num_heads,查询或者“键-值”对的个数,# num_hiddens/num_heads)queries = transpose_qkv(self.W_q(queries), self.num_heads)keys = transpose_qkv(self.W_k(keys), self.num_heads)values = transpose_qkv(self.W_v(values), self.num_heads)if valid_lens is not None:# 在轴0,将第一项(标量或者矢量)复制num_heads次,# 然后如此复制第二项,然后诸如此类。valid_lens = torch.repeat_interleave(valid_lens, repeats=self.num_heads, dim=0)# output的形状:(batch_size*num_heads,查询的个数,# num_hiddens/num_heads)output = self.attention(queries, keys, values, valid_lens)# output_concat的形状:(batch_size,查询的个数,num_hiddens)output_concat = transpose_output(output, self.num_heads)return self.W_o(output_concat)#@save
def transpose_qkv(X, num_heads):"""为了多注意力头的并行计算而变换形状"""# 输入X的形状:(batch_size,查询或者“键-值”对的个数,num_hiddens)# 输出X的形状:(batch_size,查询或者“键-值”对的个数,num_heads,# num_hiddens/num_heads)X = X.reshape(X.shape[0], X.shape[1], num_heads, -1)# 输出X的形状:(batch_size,num_heads,查询或者“键-值”对的个数,# num_hiddens/num_heads)X = X.permute(0, 2, 1, 3)# 最终输出的形状:(batch_size*num_heads,查询或者“键-值”对的个数,# num_hiddens/num_heads)return X.reshape(-1, X.shape[2], X.shape[3])#@save
def transpose_output(X, num_heads):"""逆转transpose_qkv函数的操作"""X = X.reshape(-1, num_heads, X.shape[1], X.shape[2])X = X.permute(0, 2, 1, 3)return X.reshape(X.shape[0], X.shape[1], -1)
3. Transformer代码
输出不变,模型容易叠加
重要参数:hidden-size, head
#@save
class EncoderBlock(nn.Module):"""Transformer编码器块"""def __init__(self, key_size, query_size, value_size, num_hiddens,norm_shape, ffn_num_input, ffn_num_hiddens, num_heads,dropout, use_bias=False, **kwargs):super(EncoderBlock, self).__init__(**kwargs)self.attention = d2l.MultiHeadAttention(key_size, query_size, value_size, num_hiddens, num_heads, dropout,use_bias)self.addnorm1 = AddNorm(norm_shape, dropout)self.ffn = PositionWiseFFN(ffn_num_input, ffn_num_hiddens, num_hiddens)self.addnorm2 = AddNorm(norm_shape, dropout)def forward(self, X, valid_lens):Y = self.addnorm1(X, self.attention(X, X, X, valid_lens))return self.addnorm2(Y, self.ffn(Y))#@save
class TransformerEncoder(d2l.Encoder):"""Transformer编码器"""def __init__(self, vocab_size, key_size, query_size, value_size,num_hiddens, norm_shape, ffn_num_input, ffn_num_hiddens,num_heads, num_layers, dropout, use_bias=False, **kwargs):super(TransformerEncoder, self).__init__(**kwargs)self.num_hiddens = num_hiddensself.embedding = nn.Embedding(vocab_size, num_hiddens)self.pos_encoding = d2l.PositionalEncoding(num_hiddens, dropout)self.blks = nn.Sequential()for i in range(num_layers):self.blks.add_module("block"+str(i),EncoderBlock(key_size, query_size, value_size, num_hiddens,norm_shape, ffn_num_input, ffn_num_hiddens,num_heads, dropout, use_bias))def forward(self, X, valid_lens, *args):# 因为位置编码值在-1和1之间,# 因此嵌入值乘以嵌入维度的平方根进行缩放,# 然后再与位置编码相加。X = self.pos_encoding(self.embedding(X) * math.sqrt(self.num_hiddens))self.attention_weights = [None] * len(self.blks)for i, blk in enumerate(self.blks):X = blk(X, valid_lens)self.attention_weights[i] = blk.attention.attention.attention_weightsreturn Xclass DecoderBlock(nn.Module):"""解码器中第i个块"""def __init__(self, key_size, query_size, value_size, num_hiddens,norm_shape, ffn_num_input, ffn_num_hiddens, num_heads,dropout, i, **kwargs):super(DecoderBlock, self).__init__(**kwargs)self.i = iself.attention1 = d2l.MultiHeadAttention(key_size, query_size, value_size, num_hiddens, num_heads, dropout)self.addnorm1 = AddNorm(norm_shape, dropout)self.attention2 = d2l.MultiHeadAttention(key_size, query_size, value_size, num_hiddens, num_heads, dropout)self.addnorm2 = AddNorm(norm_shape, dropout)self.ffn = PositionWiseFFN(ffn_num_input, ffn_num_hiddens,num_hiddens)self.addnorm3 = AddNorm(norm_shape, dropout)def forward(self, X, state):enc_outputs, enc_valid_lens = state[0], state[1]# 训练阶段,输出序列的所有词元都在同一时间处理,# 因此state[2][self.i]初始化为None。# 预测阶段,输出序列是通过词元一个接着一个解码的,# 因此state[2][self.i]包含着直到当前时间步第i个块解码的输出表示if state[2][self.i] is None:key_values = Xelse:key_values = torch.cat((state[2][self.i], X), axis=1)state[2][self.i] = key_valuesif self.training:batch_size, num_steps, _ = X.shape# dec_valid_lens的开头:(batch_size,num_steps),# 其中每一行是[1,2,...,num_steps]dec_valid_lens = torch.arange(1, num_steps + 1, device=X.device).repeat(batch_size, 1)else:dec_valid_lens = None# 自注意力X2 = self.attention1(X, key_values, key_values, dec_valid_lens)Y = self.addnorm1(X, X2)# 编码器-解码器注意力。# enc_outputs的开头:(batch_size,num_steps,num_hiddens)Y2 = self.attention2(Y, enc_outputs, enc_outputs, enc_valid_lens)Z = self.addnorm2(Y, Y2)return self.addnorm3(Z, self.ffn(Z)), stateclass TransformerDecoder(d2l.AttentionDecoder):def __init__(self, vocab_size, key_size, query_size, value_size,num_hiddens, norm_shape, ffn_num_input, ffn_num_hiddens,num_heads, num_layers, dropout, **kwargs):super(TransformerDecoder, self).__init__(**kwargs)self.num_hiddens = num_hiddensself.num_layers = num_layersself.embedding = nn.Embedding(vocab_size, num_hiddens)self.pos_encoding = d2l.PositionalEncoding(num_hiddens, dropout)self.blks = nn.Sequential()for i in range(num_layers):self.blks.add_module("block"+str(i),DecoderBlock(key_size, query_size, value_size, num_hiddens,norm_shape, ffn_num_input, ffn_num_hiddens,num_heads, dropout, i))self.dense = nn.Linear(num_hiddens, vocab_size)def init_state(self, enc_outputs, enc_valid_lens, *args):return [enc_outputs, enc_valid_lens, [None] * self.num_layers]def forward(self, X, state):X = self.pos_encoding(self.embedding(X) * math.sqrt(self.num_hiddens))self._attention_weights = [[None] * len(self.blks) for _ in range (2)]for i, blk in enumerate(self.blks):X, state = blk(X, state)# 解码器自注意力权重self._attention_weights[0][i] = blk.attention1.attention.attention_weights# “编码器-解码器”自注意力权重self._attention_weights[1][i] = blk.attention2.attention.attention_weightsreturn self.dense(X), state@propertydef attention_weights(self):return self._attention_weights
4. QA
14 可能区别不大
15 看芯片运算力多钱
16 transformer架构
17 concat在保留信息方面比加权平均好
18
19 无
20 n个小的attention,类似卷积多通道
21 no https://zhuanlan.zhihu.com/p/674797180
22 bert gpt 有硬件要求
23 没有实际意义
24 一般选hidden-size 256 1024等
25 变种 不是标准正态
26 bert只有encoder
27 可以 图片扣出很多batch就可以认为是一个序列
29 可以先用bert做预处理,提取特征。
30 没什么联系 位置编码 和自注意力有点关系
31 也可以 用的不多 attention比cnn要好,视野广,bert一层可以看到很长的信息–整张图片的信息。