PyTorch从零开始实现Transformer

自注意力

计算公式

代码实现

class SelfAttention(nn.Module):def __init__(self, embed_size, heads):super(SelfAttention, self).__init__()self.embed_size = embed_sizeself.heads = headsself.head_dim = embed_size // headsassert (self.head_dim * heads == embed_size),  "Embed size needs  to  be div by heads"self.values = nn.Linear(self.head_dim, self.head_dim, bias=False)self.keys = nn.Linear(self.head_dim, self.head_dim, bias=False)self.queries = nn.Linear(self.head_dim, self.head_dim, bias=False)self.fc_out = nn.Linear(heads*self.head_dim, embed_size)def forward(self, values, keys, query, mask):N = query.shape[0] # the number of training examplesvalue_len, key_len, query_len = values.shape[1], keys.shape[1], query.shape[1]# Split embedding into self.heads piecesvalues = values.reshape(N, value_len, self.heads, self.head_dim)keys = keys.reshape(N, key_len, self.heads, self.head_dim)queries = query.reshape(N, query_len, self.heads, self.head_dim)values = self.values(values)keys = self.keys(keys)queries = self.queries(queries)energy = torch.einsum("nqhd,nkhd->nhqk", [queries, keys]) # 矩阵乘法，使用爱因斯坦标记法# queries shape: (N, query_len, heads, heads_dim)# keys shape: (N, key_len, heads, heads_dim)# energy shape: (N, heads, query_len, key_len)if mask is not None:energy = energy.masked_fill(mask==0, float("-1e20")) #Fills elements of self tensor with value where mask is Trueattention = torch.softmax(energy / (self.embed_size ** (1/2)), dim=3)out = torch.einsum("nhql, nlhd->nqhd", [attention, values]).reshape(N, query_len, self.heads*self.head_dim) # 矩阵乘法，使用爱因斯坦标记法einsum# attention shape: (N, heads, query_len, key_len)# values shape: (N, value_len, heads, head_dim)# after einsum (N, query_len, heads, head_dim) then flatten last two dimensionsout = self.fc_out(out)return out

Transformer块

我们把Transfomer块定义为如下图所示的结构，这个Transformer块在编码器和解码器中都有出现过。

代码实现

class TransformerBlock(nn.Module):def __init__(self, embed_size, heads, dropout, forward_expansion):super(TransformerBlock, self).__init__()self.attention = SelfAttention(embed_size, heads)self.norm1 = nn.LayerNorm(embed_size)self.norm2 = nn.LayerNorm(embed_size)self.feed_forward = nn.Sequential(nn.Linear(embed_size, forward_expansion*embed_size),nn.ReLU(),nn.Linear(forward_expansion*embed_size, embed_size))self.dropout = nn.Dropout(dropout)def forward(self, value, key, query, mask):attention = self.attention(value, key, query, mask)x = self.dropout(self.norm1(attention + query))forward = self.feed_forward(x)out = self.dropout(self.norm2(forward + x))return out

编码器

编码器结构如下所示，Inputs经过Input Embedding 和Positional Encoding之后，通过多个Transformer块

代码实现

class Encoder(nn.Module):def __init__(self, src_vocab_size,embed_size,num_layers,heads,device,forward_expansion,dropout,max_length):super(Encoder, self).__init__()self.embed_size = embed_sizeself.device = deviceself.word_embedding = nn.Embedding(src_vocab_size, embed_size)self.position_embedding = nn.Embedding(max_length, embed_size)self.layers = nn.ModuleList([TransformerBlock(embed_size,heads,dropout=dropout,forward_expansion=forward_expansion)for _ in range(num_layers)])self.dropout = nn.Dropout(dropout)def forward(self, x, mask):N, seq_lengh = x.shapepositions = torch.arange(0, seq_lengh).expand(N, seq_lengh).to(self.device)out = self.dropout(self.word_embedding(x) + self.position_embedding(positions))for layer in self.layers:out = layer(out, out, out, mask)return out

解码器块

解码器块结构如下图所示

代码实现

class DecoderBlock(nn.Module):def __init__(self, embed_size, heads, forward_expansion, dropout, device):super(DecoderBlock, self).__init__()self.attention = SelfAttention(embed_size, heads)self.norm = nn.LayerNorm(embed_size)self.transformer_block = TransformerBlock(embed_size, heads, dropout, forward_expansion)self.dropout = nn.Dropout(dropout)def forward(self, x, value, key, src_mask, trg_mask):attention = self.attention(x, x, x, trg_mask)query = self.dropout(self.norm(attention + x))out = self.transformer_block(value, key, query, src_mask)return out

解码器

解码器块加上word embedding 和 positional embedding之后构成解码器

代码实现

class Decoder(nn.Module):def __init__(self, trg_vocab_size, embed_size, num_layers, heads, forward_expansion, dropout, device, max_length):super(Decoder, self).__init__()self.device = deviceself.word_embedding = nn.Embedding(trg_vocab_size, embed_size)self.position_embedding = nn.Embedding(max_length, embed_size)self.layers = nn.ModuleList([DecoderBlock(embed_size, heads, forward_expansion, dropout, device)for _ in range(num_layers)])self.fc_out = nn.Linear(embed_size, trg_vocab_size)self.dropout = nn.Dropout(dropout)def forward(self, x, enc_out, src_mask, trg_mask):N, seq_length = x.shapepositions = torch.arange(0, seq_length).expand(N, seq_length).to(self.device)x = self.dropout((self.word_embedding(x) + self.position_embedding(positions)))for layer in self.layers:x = layer(x, enc_out, enc_out, src_mask, trg_mask)out = self.fc_out(x)return out

整个Transformer

代码实现

class Transformer(nn.Module):def __init__(self,src_vocab_size, trg_vocab_size,src_pad_idx,trg_pad_idx,embed_size=256,num_layers=6,forward_expansion=4,heads=8,dropout=0,device="cuda",max_length=100):super(Transformer, self).__init__()self.encoder = Encoder(src_vocab_size,embed_size,num_layers,heads,device,forward_expansion,dropout,max_length)self.decoder = Decoder(trg_vocab_size,embed_size,num_layers,heads,forward_expansion,dropout,device,max_length)self.src_pad_idx = src_pad_idxself.trg_pad_idx = trg_pad_idxself.device = devicedef make_src_mask(self, src):src_mask = (src != self.src_pad_idx).unsqueeze(1).unsqueeze(2)#(N, 1, 1, src_len)return src_mask.to(self.device)def make_trg_mask(self, trg):N, trg_len = trg.shapetrg_mask = torch.tril(torch.ones((trg_len, trg_len))).expand(N, 1, trg_len, trg_len)return trg_mask.to(self.device)def forward(self, src, trg):src_mask = self.make_src_mask(src)trg_mask = self.make_trg_mask(trg)enc_src = self.encoder(src, src_mask)out = self.decoder(trg, enc_src, src_mask,  trg_mask)return out

参考来源

[1] https://www.youtube.com/watch?v=U0s0f995w14
[2] https://github.com/aladdinpersson/Machine-Learning-Collection/blob/master/ML/Pytorch/more_advanced/transformer_from_scratch/transformer_from_scratch.py

[3] https://arxiv.org/abs/1706.03762
[4] https://www.youtube.com/watch?v=pkVwUVEHmfI

全部代码（可直接运行）

import torch
import torch.nn as nnclass SelfAttention(nn.Module):def __init__(self, embed_size, heads):super(SelfAttention, self).__init__()self.embed_size = embed_sizeself.heads = headsself.head_dim = embed_size // headsassert (self.head_dim * heads == embed_size),  "Embed size needs  to  be div by heads"self.values = nn.Linear(self.head_dim, self.head_dim, bias=False)self.keys = nn.Linear(self.head_dim, self.head_dim, bias=False)self.queries = nn.Linear(self.head_dim, self.head_dim, bias=False)self.fc_out = nn.Linear(heads*self.head_dim, embed_size)def forward(self, values, keys, query, mask):N = query.shape[0] # the number of training examplesvalue_len, key_len, query_len = values.shape[1], keys.shape[1], query.shape[1]# Split embedding into self.heads piecesvalues = values.reshape(N, value_len, self.heads, self.head_dim)keys = keys.reshape(N, key_len, self.heads, self.head_dim)queries = query.reshape(N, query_len, self.heads, self.head_dim)values = self.values(values)keys = self.keys(keys)queries = self.queries(queries)energy = torch.einsum("nqhd,nkhd->nhqk", [queries, keys])# queries shape: (N, query_len, heads, heads_dim)# keys shape: (N, key_len, heads, heads_dim)# energy shape: (N, heads, query_len, key_len)if mask is not None:energy = energy.masked_fill(mask==0, float("-1e20")) #Fills elements of self tensor with value where mask is Trueattention = torch.softmax(energy / (self.embed_size ** (1/2)), dim=3)out = torch.einsum("nhql, nlhd->nqhd", [attention, values]).reshape(N, query_len, self.heads*self.head_dim)# attention shape: (N, heads, query_len, key_len)# values shape: (N, value_len, heads, head_dim)# after einsum (N, query_len, heads, head_dim) then flatten last two dimensionsout = self.fc_out(out)return outclass TransformerBlock(nn.Module):def __init__(self, embed_size, heads, dropout, forward_expansion):super(TransformerBlock, self).__init__()self.attention = SelfAttention(embed_size, heads)self.norm1 = nn.LayerNorm(embed_size)self.norm2 = nn.LayerNorm(embed_size)self.feed_forward = nn.Sequential(nn.Linear(embed_size, forward_expansion*embed_size),nn.ReLU(),nn.Linear(forward_expansion*embed_size, embed_size))self.dropout = nn.Dropout(dropout)def forward(self, value, key, query, mask):attention = self.attention(value, key, query, mask)x = self.dropout(self.norm1(attention + query))forward = self.feed_forward(x)out = self.dropout(self.norm2(forward + x))return outclass Encoder(nn.Module):def __init__(self, src_vocab_size,embed_size,num_layers,heads,device,forward_expansion,dropout,max_length):super(Encoder, self).__init__()self.embed_size = embed_sizeself.device = deviceself.word_embedding = nn.Embedding(src_vocab_size, embed_size)self.position_embedding = nn.Embedding(max_length, embed_size)self.layers = nn.ModuleList([TransformerBlock(embed_size,heads,dropout=dropout,forward_expansion=forward_expansion)for _ in range(num_layers)])self.dropout = nn.Dropout(dropout)def forward(self, x, mask):N, seq_lengh = x.shapepositions = torch.arange(0, seq_lengh).expand(N, seq_lengh).to(self.device)out = self.dropout(self.word_embedding(x) + self.position_embedding(positions))for layer in self.layers:out = layer(out, out, out, mask)return outclass DecoderBlock(nn.Module):def __init__(self, embed_size, heads, forward_expansion, dropout, device):super(DecoderBlock, self).__init__()self.attention = SelfAttention(embed_size, heads)self.norm = nn.LayerNorm(embed_size)self.transformer_block = TransformerBlock(embed_size, heads, dropout, forward_expansion)self.dropout = nn.Dropout(dropout)def forward(self, x, value, key, src_mask, trg_mask):attention = self.attention(x, x, x, trg_mask)query = self.dropout(self.norm(attention + x))out = self.transformer_block(value, key, query, src_mask)return outclass Decoder(nn.Module):def __init__(self, trg_vocab_size, embed_size, num_layers, heads, forward_expansion, dropout, device, max_length):super(Decoder, self).__init__()self.device = deviceself.word_embedding = nn.Embedding(trg_vocab_size, embed_size)self.position_embedding = nn.Embedding(max_length, embed_size)self.layers = nn.ModuleList([DecoderBlock(embed_size, heads, forward_expansion, dropout, device)for _ in range(num_layers)])self.fc_out = nn.Linear(embed_size, trg_vocab_size)self.dropout = nn.Dropout(dropout)def forward(self, x, enc_out, src_mask, trg_mask):N, seq_length = x.shapepositions = torch.arange(0, seq_length).expand(N, seq_length).to(self.device)x = self.dropout((self.word_embedding(x) + self.position_embedding(positions)))for layer in self.layers:x = layer(x, enc_out, enc_out, src_mask, trg_mask)out = self.fc_out(x)return outclass Transformer(nn.Module):def __init__(self,src_vocab_size, trg_vocab_size,src_pad_idx,trg_pad_idx,embed_size=256,num_layers=6,forward_expansion=4,heads=8,dropout=0,device="cuda",max_length=100):super(Transformer, self).__init__()self.encoder = Encoder(src_vocab_size,embed_size,num_layers,heads,device,forward_expansion,dropout,max_length)self.decoder = Decoder(trg_vocab_size,embed_size,num_layers,heads,forward_expansion,dropout,device,max_length)self.src_pad_idx = src_pad_idxself.trg_pad_idx = trg_pad_idxself.device = devicedef make_src_mask(self, src):src_mask = (src != self.src_pad_idx).unsqueeze(1).unsqueeze(2)#(N, 1, 1, src_len)return src_mask.to(self.device)def make_trg_mask(self, trg):N, trg_len = trg.shapetrg_mask = torch.tril(torch.ones((trg_len, trg_len))).expand(N, 1, trg_len, trg_len)return trg_mask.to(self.device)def forward(self, src, trg):src_mask = self.make_src_mask(src)trg_mask = self.make_trg_mask(trg)enc_src = self.encoder(src, src_mask)out = self.decoder(trg, enc_src, src_mask,  trg_mask)return outif __name__ == "__main__":device = torch.device("cuda" if torch.cuda.is_available() else "cpu")print(device)x = torch.tensor([[1, 5, 6, 4, 3, 9, 5, 2, 0], [1, 8, 7, 3, 4, 5, 6, 7, 2]]).to(device)trg = torch.tensor([[1, 7, 4, 3, 5, 9, 2, 0], [1, 5, 6, 2, 4, 7, 6, 2]]).to(device)src_pad_idx = 0trg_pad_idx = 0src_vocab_size = 10trg_vocab_size = 10model = Transformer(src_vocab_size, trg_vocab_size, src_pad_idx, trg_pad_idx, device=device).to(device)out = model(x, trg[:, :-1])print(out.shape)