Transformer模型构建

transformer架构图
在这里插入图片描述
构建模型

def make_model(source_vocab, target_vocab, N=6, 
               d_model=512, d_ff=1000, head=8, dropout=0.1):
    """该函数用来构建模型, 有7个参数,分别是源数据特征(词汇)总数,目标数据特征(词汇)总数,
       编码器和解码器堆叠数,词向量映射维度,前馈全连接网络中变换矩阵的维度,
       多头注意力结构中的多头数,以及置零比率dropout."""

    c = copy.deepcopy
    attn = MultiHeadedAttn(head, d_model)
    ff = FeedForward(d_model, d_ff, dropout)
    position = PositionalEncoding(d_model, dropout)
    
    model = EncoderDecoder(
        Encoder(EncoderLayer(d_model, c(attn), c(ff), dropout), N),
        Decoder(DecoderLayer(d_model, c(attn), c(attn), 
                             c(ff), dropout), N),
        nn.Sequential(Embeded(d_model, source_vocab), c(position)),
        nn.Sequential(Embeded(d_model, target_vocab), c(position)),
        Generator(d_model, target_vocab))


    for p in model.parameters():
        if p.dim() > 1:
            nn.init.xavier_uniform(p)
    return model


打印输出

EncoderDecoder(
  (encoder): Encoder(
    (layers): ModuleList(
      (0): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
      (1): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
      (2): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
      (3): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
      (4): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
      (5): EncoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
    )
    (norm): LayerNorm()
  )
  (decoder): Decoder(
    (layers): ModuleList(
      (0): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (2): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
      (1): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (2): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
      (2): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (2): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
      (3): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (2): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
      (4): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (2): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
      (5): DecoderLayer(
        (self_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (src_attn): MultiHeadedAttention(
          (linears): ModuleList(
            (0): Linear(in_features=512, out_features=512, bias=True)
            (1): Linear(in_features=512, out_features=512, bias=True)
            (2): Linear(in_features=512, out_features=512, bias=True)
            (3): Linear(in_features=512, out_features=512, bias=True)
          )
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (feed_forward): PositionwiseFeedForward(
          (w1): Linear(in_features=512, out_features=2048, bias=True)
          (w2): Linear(in_features=2048, out_features=512, bias=True)
          (dropout): Dropout(p=0.1, inplace=False)
        )
        (sublayer): ModuleList(
          (0): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (1): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
          (2): SublayerConnection(
            (norm): LayerNorm()
            (dropout): Dropout(p=0.1, inplace=False)
          )
        )
      )
    )
    (norm): LayerNorm()
  )
  (src_embed): Sequential(
    (0): Embeddings(
      (lut): Embedding(11, 512)
    )
    (1): PositionalEncoding(
      (dropout): Dropout(p=0.1, inplace=False)
    )
  )
  (tgt_embed): Sequential(
    (0): Embeddings(
      (lut): Embedding(11, 512)
    )
    (1): PositionalEncoding(
      (dropout): Dropout(p=0.1, inplace=False)
    )
  )
  (generator): Generator(
    (project): Linear(in_features=512, out_features=11, bias=True)
  )
)

  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
Transformer模型是一种用于自然语言处理任务的深度学习模型,它在机器翻译、文本生成和文本分类等任务中取得了很好的效果。下面是构建Transformer模型的几个关键步骤: 1. 注意力机制(Attention Mechanism):Transformer模型的核心是自注意力机制,它能够将输入序列中的每个位置与其他位置进行交互,从而捕捉到全局的上下文信息。自注意力机制通过计算查询、键和值之间的相似度来决定每个位置对其他位置的注意力权重。 2. 编码器(Encoder):Transformer模型由多个相同结构的编码器堆叠而成。每个编码器由多头注意力机制和前馈神经网络组成。多头注意力机制可以同时学习多种不同的上下文表示,而前馈神经网络则能够对每个位置的特征进行非线性变换。 3. 解码器(Decoder):在机器翻译等任务中,Transformer模型还包括一个解码器。解码器除了具有编码器的注意力机制和前馈神经网络外,还引入了一个额外的注意力机制,用于对编码器输出进行关注。 4. 位置编码(Positional Encoding):为了将序列中的位置信息引入模型Transformer模型使用位置编码来表示每个位置的信息。位置编码是一个固定的向量,它与输入的词向量相加后作为模型的输入。 5. 残差连接(Residual Connection)和层归一化(Layer Normalization):为了避免深层网络中的梯度消失和梯度爆炸问题,Transformer模型在每个子层的输入和输出之间引入了残差连接,并在每个子层后进行层归一化操作。 以上是构建Transformer模型的主要步骤。通过合理设计模型结构和训练方法,Transformer模型能够有效地捕捉输入序列的上下文信息,从而提升自然语言处理任务的性能。

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值