Datawhale - Hello Transformer

李宏毅老师的transformer讲解的非常细致，可以看这个视频入门

模型结构概览

模型输入

Encoder

Decoder

代码

# -*- coding: utf-8 -*-
"""

transformer 网络结构

@author: [email protected]
modified from a great tutorial: http://nlp.seas.harvard.edu/2018/04/03/attention.html
"""
import math
import copy
import time
import numpy as np

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable


# Model Architecture
class EncoderDecoder(nn.Module):
    """
    A standard Encoder-Decoder architecture. 
    Base for this and many other models.
    """
    def __init__(self, encoder, decoder, src_embed, tgt_embed, generator):
        super(EncoderDecoder, self).__init__()
        self.encoder = encoder
        self.decoder = decoder
        self.src_embed = src_embed    # input embedding module(input embedding + positional encode)
        self.tgt_embed = tgt_embed    # ouput embedding module
        self.generator = generator    # output generation module
        
    def forward(self, src, tgt, src_mask, tgt_mask):
        "Take in and process masked src and target sequences."
        memory = self.encode(src, src_mask)
        res = self.decode(memory, src_mask, tgt, tgt_mask)
        return res
    
    def encode(self, src, src_mask):
        src_embedds = self.src_embed(src)
        return self.encoder(src_embedds, src_mask)
    
    def decode(self, memory, src_mask, tgt, tgt_mask):
        target_embedds = self.tgt_embed(tgt)
        return self.decoder(target_embedds, memory, src_mask, tgt_mask)


class Generator(nn.Module):
    "Define standard linear + softmax generation step."
    def __init__(self, d_model, vocab):
        super(Generator, self).__init__()
        self.proj = nn.Linear(d_model, vocab)

    def forward(self, x):
        return F.log_softmax(self.proj(x), dim=-1)


def clones(module, N):
    "Produce N identical layers."
    return nn.ModuleList([copy.deepcopy(module) for _ in range(N)])


class Encoder(nn.Module):
    """
    Encoder
    The encoder is composed of a stack of N=6 identical layers.
    """
    def __init__(self, layer, N):
        super(Encoder, self).__init__()
        self.layers = clones(layer, N)
        self.norm = LayerNorm(layer.size)
        
    def forward(self, x, mask):
        "Pass the input (and mask) through each layer in turn."
        for layer in self.layers:
            x = layer(x, mask)
        return self.norm(x)

# We employ a residual connection around each of the two sub-layers, followed by layer normalization
class LayerNorm(nn.Module):
    "Construct a layernorm module (See citation for details)."
    def __init__(self, feature_size, eps=1e-6):
        super(LayerNorm, self).__init__()
        self.a_2 = nn.Parameter(torch.ones(feature_size))
        self.b_2 = nn.Parameter(torch.zeros(feature_size))
        self.eps = eps

    def forward(self, x):
        mean = x.mean(-1, keepdim=True)
        std = x.std(-1, keepdim=True)
        return self.a_2 * (x - mean) / (std + self.eps) + self.b_2


class SublayerConnection(nn.Module):
    """
    实现子层连接结构的类
    """
    def __init__(self, size, dropout):
        super(SublayerConnection, self).__init__()
        self.norm = LayerNorm(size)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x, sublayer):
        "Apply residual connection to any sublayer with the same size."

        # 原paper的方案
        #sublayer_out = sublayer(x)
        #x_norm = self.norm(x + self.dropout(sublayer_out))

        # 稍加调整的版本
        sublayer_out = sublayer(x)
        sublayer_out = self.dropout(sublayer_out)
        x_norm = x + self.norm(sublayer_out)
        return x_norm


class EncoderLayer(nn.Module):
    "EncoderLayer is made up of two sublayer: self-attn and feed forward"
    def __init__(self, size, self_attn, feed_forward, dropout):
        super(EncoderLayer, self).__init__()
        self.self_attn = self_attn
        self.feed_forward = feed_forward
        self.sublayer = clones(SublayerConnection(size, dropout), 2)
        self.size = size   # embedding's dimention of model, 默认512

    def forward(self, x, mask):
        # attention sub layer
        x = self.sublayer[0](x, lambda x: self.self_attn(x, x, x, mask))
        # feed forward sub layer
        z = self.sublayer[1](x, self.feed_forward)
        return z


# Decoder
# The decoder is also composed of a stack of N=6 identical layers.

class Decoder(nn.Module):
    "Generic N layer decoder with masking."
    def __init__(self, layer, N):
        super(Decoder, self).__init__()
        self.layers = clones(layer, N)
        self.norm = LayerNorm(layer.size)
        
    def forward(self, x, memory, src_mask, tgt_mask):
        for layer in self.layers:
            x = layer(x, memory, src_mask, tgt_mask)
        return self.norm(x)

class DecoderLayer(nn.Module):
    "Decoder is made of self-attn, src-attn, and feed forward (defined below)"
    def __init__(self, size, self_attn, src_attn, feed_forward, dropout):
        super(DecoderLayer, self).__init__()
        self.size = size
        self.self_attn = self_attn
        self.src_attn = src_attn
        self.feed_forward = feed_forward
        self.sublayer = clones(SublayerConnection(size, dropout), 3)
 
    def forward(self, x, memory, src_mask, tgt_mask):
        "Follow Figure 1 (right) for connections."
        m = memory
        x = self.sublayer[0](x, lambda x: self.self_attn(x, x, x, tgt_mask))
        x = self.sublayer[1](x, lambda x: self.src_attn(x, m, m, src_mask))
        return self.sublayer[2](x, self.feed_forward)


def subsequent_mask(size):
    "Mask out subsequent positions."
    attn_shape = (1, size, size)
    subsequent_mask = np.triu(np.ones(attn_shape), k=1).astype('uint8')
    return torch.from_numpy(subsequent_mask) == 0


# Attention
def attention(query, key, value, mask=None, dropout=None):
    "Compute 'Scaled Dot Product Attention'"
    d_k = query.size(-1)
    scores = torch.matmul(query, key.transpose(-2, -1)) / math.sqrt(d_k)
    if mask is not None:
        scores = scores.masked_fill(mask == 0, -1e9)
    p_attn = F.softmax(scores, dim = -1)
    if dropout is not None:
        p_attn = dropout(p_attn)
    return torch.matmul(p_attn, value), p_attn


class MultiHeadedAttention(nn.Module):
    def __init__(self, h, d_model, dropout=0.1):
        "Take in model size and number of heads."
        super(MultiHeadedAttention, self).__init__()
        assert d_model % h == 0
        # We assume d_v always equals d_k
        self.d_k = d_model // h
        self.h = h
        self.linears = clones(nn.Linear(d_model, d_model), 4)
        self.attn = None
        self.dropout = nn.Dropout(p=dropout)
        
    def forward(self, query, key, value, mask=None):
        "Implements Figure 2"
        if mask is not None:
            # Same mask applied to all h heads.
            mask = mask.unsqueeze(1)
        nbatches = query.size(0)
        
        # 1) Do all the linear projections in batch from d_model => h x d_k 
        query, key, value = \
            [l(x).view(nbatches, -1, self.h, self.d_k).transpose(1, 2)
             for l, x in zip(self.linears, (query, key, value))]
        
        # 2) Apply attention on all the projected vectors in batch. 
        x, self.attn = attention(query, key, value, mask=mask, 
                                 dropout=self.dropout)
        
        # 3) "Concat" using a view and apply a final linear. 
        x = x.transpose(1, 2).contiguous() \
             .view(nbatches, -1, self.h * self.d_k)
        return self.linears[-1](x)


class PositionwiseFeedForward(nn.Module):
    "Implements FFN equation."
    def __init__(self, d_model, d_ff, dropout=0.1):
        super(PositionwiseFeedForward, self).__init__()
        self.w_1 = nn.Linear(d_model, d_ff)
        self.w_2 = nn.Linear(d_ff, d_model)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x):
        return self.w_2(self.dropout(F.relu(self.w_1(x))))


# Embeddings and Softmax
class Embeddings(nn.Module):
    def __init__(self, d_model, vocab):
        super(Embeddings, self).__init__()
        self.lut = nn.Embedding(vocab, d_model)
        self.d_model = d_model

    def forward(self, x):
        embedds = self.lut(x)
        return embedds * math.sqrt(self.d_model)    # TODO 这里的归一化操作的目的?


# Positional Encoding
class PositionalEncoding(nn.Module):
    "Implement the PE function."
    def __init__(self, d_model, dropout, max_len=5000):
        """
        位置编码器类的初始化函数
        
        共有三个参数，分别是
        d_model：词嵌入维度
        dropout: dropout触发比率
        max_len：每个句子的最大长度
        """
        super(PositionalEncoding, self).__init__()
        self.dropout = nn.Dropout(p=dropout)
        
        # Compute the positional encodings
        # 注意下面代码的计算方式与公式中给出的是不同的，但是是等价的，你可以尝试简单推导证明一下。
        # 这样计算是为了避免中间的数值计算结果超出float的范围，
        pe = torch.zeros(max_len, d_model)
        position = torch.arange(0, max_len).unsqueeze(1)
        div_term = torch.exp(torch.arange(0, d_model, 2) *
                             -(math.log(10000.0) / d_model))
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        pe = pe.unsqueeze(0)
        self.register_buffer('pe', pe)
        
    def forward(self, x):
        x = x + Variable(self.pe[:, :x.size(1)], requires_grad=False)
        return self.dropout(x)


# Full Model
def make_model(src_vocab, tgt_vocab, N=6, d_model=512, d_ff=2048, h=8, dropout=0.1):
    """
    构建模型
    params:
        src_vocab:
        tgt_vocab:
        N: 编码器和解码器堆叠基础模块的个数
        d_model: 模型中embedding的size，默认512
        d_ff: FeedForward Layer层中embedding的size，默认2048
        h: MultiHeadAttention中多头的个数，必须被d_model整除
        dropout:
    """
    c = copy.deepcopy
    attn = MultiHeadedAttention(h, d_model)
    ff = PositionwiseFeedForward(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(Embeddings(d_model, src_vocab), c(position)),
        nn.Sequential(Embeddings(d_model, tgt_vocab), c(position)),
        Generator(d_model, tgt_vocab))
    
    # This was important from their code. 
    # Initialize parameters with Glorot / fan_avg.
    for p in model.parameters():
        if p.dim() > 1:
            nn.init.xavier_uniform_(p)
    return model



if __name__ == "__main__":

    print("\n-----------------------")
    print("test subsequect_mask")
    temp_mask = subsequent_mask(4)
    print(temp_mask)

    print("\n-----------------------")
    print("test build model")
    tmp_model = make_model(10, 10, 2)
    print(tmp_model)

自己碰到的问题

1. register_buffer: 在内存中定一个常量，模型保存和加载的时候可以写入和读出。
2. torch.unsqueeze: 对数据维度进行扩充
3. 在代码里,self_attention层处理decoder的第二个multi-head attention层输入Q!=K=V之外，其他的Q=K=V. 但是在李宏毅的课程里, Q,K,V都是由输入X经过某个变换得到的。