transformer架构图
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)
)
)