一、Transformer 结构图
如下图,为 Transformer 的整体结构图,左侧为 Transformer Encoder Block,右侧为 Transformer Decoder Block。
在整体使用中,两个 Block 均被多次重复使用,即上一 Block 的输出向量作为下一 Block 的输入向量。
二、代码实现
由(一)所介绍,Transformer 是由 TransformerEncoder 和 TransformerDecoder 组成,而这两者又分别是由多个 TransformerEncoderLayers 和 TransformerDecoderLayers 组成(或理解为多个 Block 组成)
下图代码,建议对照上图内部结构去看,更容易理解一些。
1.1)TransformerEncoderLayer 代码:
# Transformer Encoder Layer
class TransformerEncoderLayer(Module):
r"""TransformerEncoderLayer is made up of self-attn and feedforward network.
This standard encoder layer is based on the paper "Attention Is All You Need".
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez,
Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in
Neural Information Processing Systems, pages 6000-6010. Users may modify or implement
in a different way during application.
Args:
d_model: the number of expected features in the input (required).
nhead: the number of heads in the multiheadattention models (required).
dim_feedforward: the dimension of the feedforward network model (default=2048).
dropout: the dropout value (default=0.1).
activation: the activation function of intermediate layer, relu or gelu (default=relu).
Examples::
>>> encoder_layer = nn.TransformerEncoderLayer(d_model=512, nhead=8)
>>> src = torch.rand(10, 32, 512)
>>> out = encoder_layer(src)
"""
def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation="relu"):
super(TransformerEncoderLayer, self).__init__()
self.self_attn = MultiheadAttention(d_model, nhead, dropout=dropout)
# Implementation of Feedforward model
self.linear1 = Linear(d_model, dim_feedforward)
self.dropout = Dropout(dropout)
self.linear2 = Linear(dim_feedforward, d_model)
self.norm1 = LayerNorm(d_model)
self.norm2 = LayerNorm(d_model)
self.dropout1 = Dropout(dropout)
self.dropout2 = Dropout(dropout)
self.activation = _get_activation_fn(activation)
def __setstate__(self, state):
if 'activation' not in state:
state['activation'] = F.relu
super(TransformerEncoderLayer, self).__setstate__(state)
def forward(self, src: Tensor, src_mask: Optional[Tensor] = None, src_key_padding_mask: Optional[Tensor] = None) -> Tensor:
r"""Pass the input through the encoder layer.
Args:
src: the sequence to the encoder layer (required).
src_mask: the mask for the src sequence (optional).
src_key_padding_mask: the mask for the src keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
# look the picture of transformer encoder
# Norm(src+Dropout(self_attention(src)))
src2 = self.self_attn(src, src, src, attn_mask=src_mask,
key_padding_mask=src_key_padding_mask)[0]
src = src + self.dropout1(src2)
src = self.norm1(src)
# Norm(src+Dropout(Feedforward()))
src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
src = src + self.dropout2(src2)
src = self.norm2(src)
return src
1.2)TransformerEncoder 代码(多次执行 TransformerEncoderLayer 里的内容):
# A stack of N encoder layers
class TransformerEncoder(Module):
r"""TransformerEncoder is a stack of N encoder layers
Args:
encoder_layer: an instance of the TransformerEncoderLayer() class (required).
num_layers: the number of sub-encoder-layers in the encoder (required).
norm: the layer normalization component (optional).
Examples::
>>> encoder_layer = nn.TransformerEncoderLayer(d_model=512, nhead=8)
>>> transformer_encoder = nn.TransformerEncoder(encoder_layer, num_layers=6)
>>> src = torch.rand(10, 32, 512)
>>> out = transformer_encoder(src)
"""
__constants__ = ['norm']
def __init__(self, encoder_layer, num_layers, norm=None):
super(TransformerEncoder, self).__init__()
self.layers = _get_clones(encoder_layer, num_layers)
self.num_layers = num_layers
self.norm = norm
def forward(self, src: Tensor, mask: Optional[Tensor] = None, src_key_padding_mask: Optional[Tensor] = None) -> Tensor:
r"""Pass the input through the encoder layers in turn.
Args:
src: the sequence to the encoder (required).
mask: the mask for the src sequence (optional).
src_key_padding_mask: the mask for the src keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
output = src
for mod in self.layers:
output = mod(output, src_mask=mask, src_key_padding_mask=src_key_padding_mask)
if self.norm is not None:
output = self.norm(output)
return output
2.1)TransformerDecoderLayer 代码:
# For language reconstruct
class TransformerDecoderLayer(Module):
r"""TransformerDecoderLayer is made up of self-attn, multi-head-attn and feedforward network.
This standard decoder layer is based on the paper "Attention Is All You Need".
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez,
Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in
Neural Information Processing Systems, pages 6000-6010. Users may modify or implement
in a different way during application.
Args:
d_model: the number of expected features in the input (required).
nhead: the number of heads in the multiheadattention models (required).
dim_feedforward: the dimension of the feedforward network model (default=2048).
dropout: the dropout value (default=0.1).
activation: the activation function of intermediate layer, relu or gelu (default=relu).
Examples::
>>> decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8)
>>> memory = torch.rand(10, 32, 512)
>>> tgt = torch.rand(20, 32, 512)
>>> out = decoder_layer(tgt, memory)
"""
# d_model = 768, nhead = 8
def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation="relu"):
super(TransformerDecoderLayer, self).__init__()
self.self_attn = MultiheadAttention(d_model, nhead, dropout=dropout)
self.multihead_attn = MultiheadAttention(d_model, nhead, dropout=dropout)
# Implementation of Feedforward model
self.linear1 = Linear(d_model, dim_feedforward)
self.dropout = Dropout(dropout)
self.linear2 = Linear(dim_feedforward, d_model)
self.norm1 = LayerNorm(d_model)
self.norm2 = LayerNorm(d_model)
self.norm3 = LayerNorm(d_model)
self.dropout1 = Dropout(dropout)
self.dropout2 = Dropout(dropout)
self.dropout3 = Dropout(dropout)
self.activation = _get_activation_fn(activation)
def __setstate__(self, state):
if 'activation' not in state:
state['activation'] = F.relu
super(TransformerDecoderLayer, self).__setstate__(state)
# tgt: the sequence to the decoder layer (required). (20,1,768)
# memory: the sequence from the last layer of the encoder (required). (3600,1,768)
def forward(self, tgt: Tensor, memory: Tensor, tgt_mask: Optional[Tensor] = None, memory_mask: Optional[Tensor] = None,
tgt_key_padding_mask: Optional[Tensor] = None, memory_key_padding_mask: Optional[Tensor] = None) -> Tensor:
r"""Pass the inputs (and mask) through the decoder layer.
Args:
tgt: the sequence to the decoder layer (required).
memory: the sequence from the last layer of the encoder (required).
tgt_mask: the mask for the tgt sequence (optional).
memory_mask: the mask for the memory sequence (optional).
tgt_key_padding_mask: the mask for the tgt keys per batch (optional).
memory_key_padding_mask: the mask for the memory keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
# 类比 Transformer Decoder 的结构
# tgt = Norm(Dropout(attention(tgt,tgt,tgt))+tgt)
tgt2 = self.self_attn(tgt, tgt, tgt, attn_mask=tgt_mask, # Multihead self-attention tgt2 (20,1,768)
key_padding_mask=tgt_key_padding_mask)[0]
tgt = tgt + self.dropout1(tgt2) # tgt = tgt + dropout1(0.1,tgt2) (20,1,768)
tgt = self.norm1(tgt) # LayerNorm (1,768,60,60)
# tgt = Norm(Dropout(attention(tgt,memory,memory))+tgt)
tgt2 = self.multihead_attn(tgt, memory, memory, attn_mask=memory_mask, # Multihead self-attention tgt2 (20,1,768)
key_padding_mask=memory_key_padding_mask)[0]
tgt = tgt + self.dropout2(tgt2) # (20,1,768)
tgt = self.norm2(tgt) # (20,1,768)
tgt2 = self.linear2(self.dropout(self.activation(self.linear1(tgt)))) # tgt2 (20,1,768)
tgt = tgt + self.dropout3(tgt2)
tgt = self.norm3(tgt)
return tgt # (20,1,768)
2.2)TransformerDecoder 代码(多次执行 TransformerDecoderLayer 里的内容):
# A stack of N decoder layers
class TransformerDecoder(Module):
r"""TransformerDecoder is a stack of N decoder layers
Args:
decoder_layer: an instance of the TransformerDecoderLayer() class (required).
num_layers: the number of sub-decoder-layers in the decoder (required).
norm: the layer normalization component (optional).
Examples::
>>> decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8)
>>> transformer_decoder = nn.TransformerDecoder(decoder_layer, num_layers=6)
>>> memory = torch.rand(10, 32, 512)
>>> tgt = torch.rand(20, 32, 512)
>>> out = transformer_decoder(tgt, memory)
"""
__constants__ = ['norm']
def __init__(self, decoder_layer, num_layers, norm=None):
super(TransformerDecoder, self).__init__()
self.layers = _get_clones(decoder_layer, num_layers)
self.num_layers = num_layers
self.norm = norm
def forward(self, tgt: Tensor, memory: Tensor, tgt_mask: Optional[Tensor] = None,
memory_mask: Optional[Tensor] = None, tgt_key_padding_mask: Optional[Tensor] = None,
memory_key_padding_mask: Optional[Tensor] = None) -> Tensor:
r"""Pass the inputs (and mask) through the decoder layer in turn.
Args:
tgt: the sequence to the decoder (required).
memory: the sequence from the last layer of the encoder (required).
tgt_mask: the mask for the tgt sequence (optional).
memory_mask: the mask for the memory sequence (optional).
tgt_key_padding_mask: the mask for the tgt keys per batch (optional).
memory_key_padding_mask: the mask for the memory keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
output = tgt
for mod in self.layers:
output = mod(output, memory, tgt_mask=tgt_mask,
memory_mask=memory_mask,
tgt_key_padding_mask=tgt_key_padding_mask,
memory_key_padding_mask=memory_key_padding_mask)
if self.norm is not None:
output = self.norm(output)
return output
2.3)Transformer 代码:
a、先初始化 TransformerEncoder 和 TransformerDecoder
b、在 forward( ) 中分别调用他们
# High Architecture of Transformer encoder and Transformer decoder
class Transformer(Module):
r"""A transformer model. User is able to modify the attributes as needed. The architecture
is based on the paper "Attention Is All You Need". Ashish Vaswani, Noam Shazeer,
Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and
Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information
Processing Systems, pages 6000-6010. Users can build the BERT(https://arxiv.org/abs/1810.04805)
model with corresponding parameters.
Args:
d_model: the number of expected features in the encoder/decoder inputs (default=512).
nhead: the number of heads in the multiheadattention models (default=8).
num_encoder_layers: the number of sub-encoder-layers in the encoder (default=6).
num_decoder_layers: the number of sub-decoder-layers in the decoder (default=6).
dim_feedforward: the dimension of the feedforward network model (default=2048).
dropout: the dropout value (default=0.1).
activation: the activation function of encoder/decoder intermediate layer, relu or gelu (default=relu).
custom_encoder: custom encoder (default=None).
custom_decoder: custom decoder (default=None).
Examples::
>>> transformer_model = nn.Transformer(nhead=16, num_encoder_layers=12)
>>> src = torch.rand((10, 32, 512))
>>> tgt = torch.rand((20, 32, 512))
>>> out = transformer_model(src, tgt)
Note: A full example to apply nn.Transformer module for the word language model is available in
https://github.com/pytorch/examples/tree/master/word_language_model
"""
def __init__(self, d_model: int = 512, nhead: int = 8, num_encoder_layers: int = 6,
num_decoder_layers: int = 6, dim_feedforward: int = 2048, dropout: float = 0.1,
activation: str = "relu", custom_encoder: Optional[Any] = None, custom_decoder: Optional[Any] = None) -> None:
super(Transformer, self).__init__()
if custom_encoder is not None:
self.encoder = custom_encoder
else:
encoder_layer = TransformerEncoderLayer(d_model, nhead, dim_feedforward, dropout, activation)
encoder_norm = LayerNorm(d_model)
self.encoder = TransformerEncoder(encoder_layer, num_encoder_layers, encoder_norm)
if custom_decoder is not None:
self.decoder = custom_decoder
else:
decoder_layer = TransformerDecoderLayer(d_model, nhead, dim_feedforward, dropout, activation)
decoder_norm = LayerNorm(d_model)
self.decoder = TransformerDecoder(decoder_layer, num_decoder_layers, decoder_norm)
self._reset_parameters()
self.d_model = d_model
self.nhead = nhead
def forward(self, src: Tensor, tgt: Tensor, src_mask: Optional[Tensor] = None, tgt_mask: Optional[Tensor] = None,
memory_mask: Optional[Tensor] = None, src_key_padding_mask: Optional[Tensor] = None,
tgt_key_padding_mask: Optional[Tensor] = None, memory_key_padding_mask: Optional[Tensor] = None) -> Tensor:
r"""Take in and process masked source/target sequences.
Args:
src: the sequence to the encoder (required).
tgt: the sequence to the decoder (required).
src_mask: the additive mask for the src sequence (optional).
tgt_mask: the additive mask for the tgt sequence (optional).
memory_mask: the additive mask for the encoder output (optional).
src_key_padding_mask: the ByteTensor mask for src keys per batch (optional).
tgt_key_padding_mask: the ByteTensor mask for tgt keys per batch (optional).
memory_key_padding_mask: the ByteTensor mask for memory keys per batch (optional).
Shape:
- src: :math:`(S, N, E)`.
- tgt: :math:`(T, N, E)`.
- src_mask: :math:`(S, S)`.
- tgt_mask: :math:`(T, T)`.
- memory_mask: :math:`(T, S)`.
- src_key_padding_mask: :math:`(N, S)`.
- tgt_key_padding_mask: :math:`(N, T)`.
- memory_key_padding_mask: :math:`(N, S)`.
Note: [src/tgt/memory]_mask ensures that position i is allowed to attend the unmasked
positions. If a ByteTensor is provided, the non-zero positions are not allowed to attend
while the zero positions will be unchanged. If a BoolTensor is provided, positions with ``True``
are not allowed to attend while ``False`` values will be unchanged. If a FloatTensor
is provided, it will be added to the attention weight.
[src/tgt/memory]_key_padding_mask provides specified elements in the key to be ignored by
the attention. If a ByteTensor is provided, the non-zero positions will be ignored while the zero
positions will be unchanged. If a BoolTensor is provided, the positions with the
value of ``True`` will be ignored while the position with the value of ``False`` will be unchanged.
- output: :math:`(T, N, E)`.
Note: Due to the multi-head attention architecture in the transformer model,
the output sequence length of a transformer is same as the input sequence
(i.e. target) length of the decode.
where S is the source sequence length, T is the target sequence length, N is the
batch size, E is the feature number
Examples:
>>> output = transformer_model(src, tgt, src_mask=src_mask, tgt_mask=tgt_mask)
"""
if src.size(1) != tgt.size(1):
raise RuntimeError("the batch number of src and tgt must be equal")
if src.size(2) != self.d_model or tgt.size(2) != self.d_model:
raise RuntimeError("the feature number of src and tgt must be equal to d_model")
memory = self.encoder(src, mask=src_mask, src_key_padding_mask=src_key_padding_mask)
output = self.decoder(tgt, memory, tgt_mask=tgt_mask, memory_mask=memory_mask,
tgt_key_padding_mask=tgt_key_padding_mask,
memory_key_padding_mask=memory_key_padding_mask)
return output
def generate_square_subsequent_mask(self, sz: int) -> Tensor:
r"""Generate a square mask for the sequence. The masked positions are filled with float('-inf').
Unmasked positions are filled with float(0.0).
"""
mask = (torch.triu(torch.ones(sz, sz)) == 1).transpose(0, 1)
mask = mask.float().masked_fill(mask == 0, float('-inf')).masked_fill(mask == 1, float(0.0))
return mask
def _reset_parameters(self):
r"""Initiate parameters in the transformer model."""
for p in self.parameters():
if p.dim() > 1:
xavier_uniform_(p)
下面是完整的 transformer.py 文件:
import copy
from typing import Optional, Any
import torch
from torch import Tensor
from .. import functional as F
from .module import Module
from .activation import MultiheadAttention
from .container import ModuleList
from ..init import xavier_uniform_
from .dropout import Dropout
from .linear import Linear
from .normalization import LayerNorm
# High Architecture of Transformer encoder and Transformer decoder
class Transformer(Module):
r"""A transformer model. User is able to modify the attributes as needed. The architecture
is based on the paper "Attention Is All You Need". Ashish Vaswani, Noam Shazeer,
Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and
Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information
Processing Systems, pages 6000-6010. Users can build the BERT(https://arxiv.org/abs/1810.04805)
model with corresponding parameters.
Args:
d_model: the number of expected features in the encoder/decoder inputs (default=512).
nhead: the number of heads in the multiheadattention models (default=8).
num_encoder_layers: the number of sub-encoder-layers in the encoder (default=6).
num_decoder_layers: the number of sub-decoder-layers in the decoder (default=6).
dim_feedforward: the dimension of the feedforward network model (default=2048).
dropout: the dropout value (default=0.1).
activation: the activation function of encoder/decoder intermediate layer, relu or gelu (default=relu).
custom_encoder: custom encoder (default=None).
custom_decoder: custom decoder (default=None).
Examples::
>>> transformer_model = nn.Transformer(nhead=16, num_encoder_layers=12)
>>> src = torch.rand((10, 32, 512))
>>> tgt = torch.rand((20, 32, 512))
>>> out = transformer_model(src, tgt)
Note: A full example to apply nn.Transformer module for the word language model is available in
https://github.com/pytorch/examples/tree/master/word_language_model
"""
def __init__(self, d_model: int = 512, nhead: int = 8, num_encoder_layers: int = 6,
num_decoder_layers: int = 6, dim_feedforward: int = 2048, dropout: float = 0.1,
activation: str = "relu", custom_encoder: Optional[Any] = None, custom_decoder: Optional[Any] = None) -> None:
super(Transformer, self).__init__()
if custom_encoder is not None:
self.encoder = custom_encoder
else:
encoder_layer = TransformerEncoderLayer(d_model, nhead, dim_feedforward, dropout, activation)
encoder_norm = LayerNorm(d_model)
self.encoder = TransformerEncoder(encoder_layer, num_encoder_layers, encoder_norm)
if custom_decoder is not None:
self.decoder = custom_decoder
else:
decoder_layer = TransformerDecoderLayer(d_model, nhead, dim_feedforward, dropout, activation)
decoder_norm = LayerNorm(d_model)
self.decoder = TransformerDecoder(decoder_layer, num_decoder_layers, decoder_norm)
self._reset_parameters()
self.d_model = d_model
self.nhead = nhead
def forward(self, src: Tensor, tgt: Tensor, src_mask: Optional[Tensor] = None, tgt_mask: Optional[Tensor] = None,
memory_mask: Optional[Tensor] = None, src_key_padding_mask: Optional[Tensor] = None,
tgt_key_padding_mask: Optional[Tensor] = None, memory_key_padding_mask: Optional[Tensor] = None) -> Tensor:
r"""Take in and process masked source/target sequences.
Args:
src: the sequence to the encoder (required).
tgt: the sequence to the decoder (required).
src_mask: the additive mask for the src sequence (optional).
tgt_mask: the additive mask for the tgt sequence (optional).
memory_mask: the additive mask for the encoder output (optional).
src_key_padding_mask: the ByteTensor mask for src keys per batch (optional).
tgt_key_padding_mask: the ByteTensor mask for tgt keys per batch (optional).
memory_key_padding_mask: the ByteTensor mask for memory keys per batch (optional).
Shape:
- src: :math:`(S, N, E)`.
- tgt: :math:`(T, N, E)`.
- src_mask: :math:`(S, S)`.
- tgt_mask: :math:`(T, T)`.
- memory_mask: :math:`(T, S)`.
- src_key_padding_mask: :math:`(N, S)`.
- tgt_key_padding_mask: :math:`(N, T)`.
- memory_key_padding_mask: :math:`(N, S)`.
Note: [src/tgt/memory]_mask ensures that position i is allowed to attend the unmasked
positions. If a ByteTensor is provided, the non-zero positions are not allowed to attend
while the zero positions will be unchanged. If a BoolTensor is provided, positions with ``True``
are not allowed to attend while ``False`` values will be unchanged. If a FloatTensor
is provided, it will be added to the attention weight.
[src/tgt/memory]_key_padding_mask provides specified elements in the key to be ignored by
the attention. If a ByteTensor is provided, the non-zero positions will be ignored while the zero
positions will be unchanged. If a BoolTensor is provided, the positions with the
value of ``True`` will be ignored while the position with the value of ``False`` will be unchanged.
- output: :math:`(T, N, E)`.
Note: Due to the multi-head attention architecture in the transformer model,
the output sequence length of a transformer is same as the input sequence
(i.e. target) length of the decode.
where S is the source sequence length, T is the target sequence length, N is the
batch size, E is the feature number
Examples:
>>> output = transformer_model(src, tgt, src_mask=src_mask, tgt_mask=tgt_mask)
"""
if src.size(1) != tgt.size(1):
raise RuntimeError("the batch number of src and tgt must be equal")
if src.size(2) != self.d_model or tgt.size(2) != self.d_model:
raise RuntimeError("the feature number of src and tgt must be equal to d_model")
memory = self.encoder(src, mask=src_mask, src_key_padding_mask=src_key_padding_mask)
output = self.decoder(tgt, memory, tgt_mask=tgt_mask, memory_mask=memory_mask,
tgt_key_padding_mask=tgt_key_padding_mask,
memory_key_padding_mask=memory_key_padding_mask)
return output
def generate_square_subsequent_mask(self, sz: int) -> Tensor:
r"""Generate a square mask for the sequence. The masked positions are filled with float('-inf').
Unmasked positions are filled with float(0.0).
"""
mask = (torch.triu(torch.ones(sz, sz)) == 1).transpose(0, 1)
mask = mask.float().masked_fill(mask == 0, float('-inf')).masked_fill(mask == 1, float(0.0))
return mask
def _reset_parameters(self):
r"""Initiate parameters in the transformer model."""
for p in self.parameters():
if p.dim() > 1:
xavier_uniform_(p)
# A stack of N encoder layers
class TransformerEncoder(Module):
r"""TransformerEncoder is a stack of N encoder layers
Args:
encoder_layer: an instance of the TransformerEncoderLayer() class (required).
num_layers: the number of sub-encoder-layers in the encoder (required).
norm: the layer normalization component (optional).
Examples::
>>> encoder_layer = nn.TransformerEncoderLayer(d_model=512, nhead=8)
>>> transformer_encoder = nn.TransformerEncoder(encoder_layer, num_layers=6)
>>> src = torch.rand(10, 32, 512)
>>> out = transformer_encoder(src)
"""
__constants__ = ['norm']
def __init__(self, encoder_layer, num_layers, norm=None):
super(TransformerEncoder, self).__init__()
self.layers = _get_clones(encoder_layer, num_layers)
self.num_layers = num_layers
self.norm = norm
def forward(self, src: Tensor, mask: Optional[Tensor] = None, src_key_padding_mask: Optional[Tensor] = None) -> Tensor:
r"""Pass the input through the encoder layers in turn.
Args:
src: the sequence to the encoder (required).
mask: the mask for the src sequence (optional).
src_key_padding_mask: the mask for the src keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
output = src
for mod in self.layers:
output = mod(output, src_mask=mask, src_key_padding_mask=src_key_padding_mask)
if self.norm is not None:
output = self.norm(output)
return output
# A stack of N decoder layers
class TransformerDecoder(Module):
r"""TransformerDecoder is a stack of N decoder layers
Args:
decoder_layer: an instance of the TransformerDecoderLayer() class (required).
num_layers: the number of sub-decoder-layers in the decoder (required).
norm: the layer normalization component (optional).
Examples::
>>> decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8)
>>> transformer_decoder = nn.TransformerDecoder(decoder_layer, num_layers=6)
>>> memory = torch.rand(10, 32, 512)
>>> tgt = torch.rand(20, 32, 512)
>>> out = transformer_decoder(tgt, memory)
"""
__constants__ = ['norm']
def __init__(self, decoder_layer, num_layers, norm=None):
super(TransformerDecoder, self).__init__()
self.layers = _get_clones(decoder_layer, num_layers)
self.num_layers = num_layers
self.norm = norm
def forward(self, tgt: Tensor, memory: Tensor, tgt_mask: Optional[Tensor] = None,
memory_mask: Optional[Tensor] = None, tgt_key_padding_mask: Optional[Tensor] = None,
memory_key_padding_mask: Optional[Tensor] = None) -> Tensor:
r"""Pass the inputs (and mask) through the decoder layer in turn.
Args:
tgt: the sequence to the decoder (required).
memory: the sequence from the last layer of the encoder (required).
tgt_mask: the mask for the tgt sequence (optional).
memory_mask: the mask for the memory sequence (optional).
tgt_key_padding_mask: the mask for the tgt keys per batch (optional).
memory_key_padding_mask: the mask for the memory keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
output = tgt
for mod in self.layers:
output = mod(output, memory, tgt_mask=tgt_mask,
memory_mask=memory_mask,
tgt_key_padding_mask=tgt_key_padding_mask,
memory_key_padding_mask=memory_key_padding_mask)
if self.norm is not None:
output = self.norm(output)
return output
# Transformer Encoder Layer
class TransformerEncoderLayer(Module):
r"""TransformerEncoderLayer is made up of self-attn and feedforward network.
This standard encoder layer is based on the paper "Attention Is All You Need".
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez,
Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in
Neural Information Processing Systems, pages 6000-6010. Users may modify or implement
in a different way during application.
Args:
d_model: the number of expected features in the input (required).
nhead: the number of heads in the multiheadattention models (required).
dim_feedforward: the dimension of the feedforward network model (default=2048).
dropout: the dropout value (default=0.1).
activation: the activation function of intermediate layer, relu or gelu (default=relu).
Examples::
>>> encoder_layer = nn.TransformerEncoderLayer(d_model=512, nhead=8)
>>> src = torch.rand(10, 32, 512)
>>> out = encoder_layer(src)
"""
def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation="relu"):
super(TransformerEncoderLayer, self).__init__()
self.self_attn = MultiheadAttention(d_model, nhead, dropout=dropout)
# Implementation of Feedforward model
self.linear1 = Linear(d_model, dim_feedforward)
self.dropout = Dropout(dropout)
self.linear2 = Linear(dim_feedforward, d_model)
self.norm1 = LayerNorm(d_model)
self.norm2 = LayerNorm(d_model)
self.dropout1 = Dropout(dropout)
self.dropout2 = Dropout(dropout)
self.activation = _get_activation_fn(activation)
def __setstate__(self, state):
if 'activation' not in state:
state['activation'] = F.relu
super(TransformerEncoderLayer, self).__setstate__(state)
def forward(self, src: Tensor, src_mask: Optional[Tensor] = None, src_key_padding_mask: Optional[Tensor] = None) -> Tensor:
r"""Pass the input through the encoder layer.
Args:
src: the sequence to the encoder layer (required).
src_mask: the mask for the src sequence (optional).
src_key_padding_mask: the mask for the src keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
# look the picture of transformer encoder
# Norm(src+Dropout(self_attention(src)))
src2 = self.self_attn(src, src, src, attn_mask=src_mask,
key_padding_mask=src_key_padding_mask)[0]
src = src + self.dropout1(src2)
src = self.norm1(src)
# Norm(src+Dropout(Feedforward()))
src2 = self.linear2(self.dropout(self.activation(self.linear1(src))))
src = src + self.dropout2(src2)
src = self.norm2(src)
return src
# For language reconstruct
class TransformerDecoderLayer(Module):
r"""TransformerDecoderLayer is made up of self-attn, multi-head-attn and feedforward network.
This standard decoder layer is based on the paper "Attention Is All You Need".
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez,
Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in
Neural Information Processing Systems, pages 6000-6010. Users may modify or implement
in a different way during application.
Args:
d_model: the number of expected features in the input (required).
nhead: the number of heads in the multiheadattention models (required).
dim_feedforward: the dimension of the feedforward network model (default=2048).
dropout: the dropout value (default=0.1).
activation: the activation function of intermediate layer, relu or gelu (default=relu).
Examples::
>>> decoder_layer = nn.TransformerDecoderLayer(d_model=512, nhead=8)
>>> memory = torch.rand(10, 32, 512)
>>> tgt = torch.rand(20, 32, 512)
>>> out = decoder_layer(tgt, memory)
"""
# d_model = 768, nhead = 8
def __init__(self, d_model, nhead, dim_feedforward=2048, dropout=0.1, activation="relu"):
super(TransformerDecoderLayer, self).__init__()
self.self_attn = MultiheadAttention(d_model, nhead, dropout=dropout)
self.multihead_attn = MultiheadAttention(d_model, nhead, dropout=dropout)
# Implementation of Feedforward model
self.linear1 = Linear(d_model, dim_feedforward)
self.dropout = Dropout(dropout)
self.linear2 = Linear(dim_feedforward, d_model)
self.norm1 = LayerNorm(d_model)
self.norm2 = LayerNorm(d_model)
self.norm3 = LayerNorm(d_model)
self.dropout1 = Dropout(dropout)
self.dropout2 = Dropout(dropout)
self.dropout3 = Dropout(dropout)
self.activation = _get_activation_fn(activation)
def __setstate__(self, state):
if 'activation' not in state:
state['activation'] = F.relu
super(TransformerDecoderLayer, self).__setstate__(state)
# tgt: the sequence to the decoder layer (required). (20,1,768)
# memory: the sequence from the last layer of the encoder (required). (3600,1,768)
def forward(self, tgt: Tensor, memory: Tensor, tgt_mask: Optional[Tensor] = None, memory_mask: Optional[Tensor] = None,
tgt_key_padding_mask: Optional[Tensor] = None, memory_key_padding_mask: Optional[Tensor] = None) -> Tensor:
r"""Pass the inputs (and mask) through the decoder layer.
Args:
tgt: the sequence to the decoder layer (required).
memory: the sequence from the last layer of the encoder (required).
tgt_mask: the mask for the tgt sequence (optional).
memory_mask: the mask for the memory sequence (optional).
tgt_key_padding_mask: the mask for the tgt keys per batch (optional).
memory_key_padding_mask: the mask for the memory keys per batch (optional).
Shape:
see the docs in Transformer class.
"""
# 类比 Transformer Decoder 的结构
# tgt = Norm(Dropout(attention(tgt,tgt,tgt))+tgt)
tgt2 = self.self_attn(tgt, tgt, tgt, attn_mask=tgt_mask, # Multihead self-attention tgt2 (20,1,768)
key_padding_mask=tgt_key_padding_mask)[0]
tgt = tgt + self.dropout1(tgt2) # tgt = tgt + dropout1(0.1,tgt2) (20,1,768)
tgt = self.norm1(tgt) # LayerNorm (1,768,60,60)
# tgt = Norm(Dropout(attention(tgt,memory,memory))+tgt)
tgt2 = self.multihead_attn(tgt, memory, memory, attn_mask=memory_mask, # Multihead self-attention tgt2 (20,1,768)
key_padding_mask=memory_key_padding_mask)[0]
tgt = tgt + self.dropout2(tgt2) # (20,1,768)
tgt = self.norm2(tgt) # (20,1,768)
tgt2 = self.linear2(self.dropout(self.activation(self.linear1(tgt)))) # tgt2 (20,1,768)
tgt = tgt + self.dropout3(tgt2)
tgt = self.norm3(tgt)
return tgt # (20,1,768)
def _get_clones(module, N):
return ModuleList([copy.deepcopy(module) for i in range(N)])
def _get_activation_fn(activation):
if activation == "relu":
return F.relu
elif activation == "gelu":
return F.gelu
raise RuntimeError("activation should be relu/gelu, not {}".format(activation))
三、Transformer 中的多头注意力机制
Transformer 中多次使用了多头注意力机制。
在 EncoderLayer 中,使用了一次多头自注意力机制。
在 DecoderLayer 中,先使用了一次多头自注意力机制,紧接着使用了一次多头非自注意力机制(k 为 tgt,q、v 为memory,是从上一个 encoder block 输出的结果)。
注意力机制的代码实现如下:
# 多头注意力机制
class MultiheadAttention(Module):
r"""Allows the model to jointly attend to information
from different representation subspaces.
See reference: Attention Is All You Need
.. math::
\text{MultiHead}(Q, K, V) = \text{Concat}(head_1,\dots,head_h)W^O
\text{where} head_i = \text{Attention}(QW_i^Q, KW_i^K, VW_i^V)
Args:
embed_dim: total dimension of the model.
num_heads: parallel attention heads.
dropout: a Dropout layer on attn_output_weights. Default: 0.0.
bias: add bias as module parameter. Default: True.
add_bias_kv: add bias to the key and value sequences at dim=0.
add_zero_attn: add a new batch of zeros to the key and
value sequences at dim=1.
kdim: total number of features in key. Default: None.
vdim: total number of features in value. Default: None.
Note: if kdim and vdim are None, they will be set to embed_dim such that
query, key, and value have the same number of features.
Examples::
>>> multihead_attn = nn.MultiheadAttention(embed_dim, num_heads)
>>> attn_output, attn_output_weights = multihead_attn(query, key, value)
"""
bias_k: Optional[torch.Tensor]
bias_v: Optional[torch.Tensor]
def __init__(self, embed_dim, num_heads, dropout=0., bias=True, add_bias_kv=False, add_zero_attn=False, kdim=None, vdim=None):
super(MultiheadAttention, self).__init__()
self.embed_dim = embed_dim
self.kdim = kdim if kdim is not None else embed_dim
self.vdim = vdim if vdim is not None else embed_dim
self._qkv_same_embed_dim = self.kdim == embed_dim and self.vdim == embed_dim
self.num_heads = num_heads
self.dropout = dropout
self.head_dim = embed_dim // num_heads
assert self.head_dim * num_heads == self.embed_dim, "embed_dim must be divisible by num_heads"
if self._qkv_same_embed_dim is False:
self.q_proj_weight = Parameter(torch.Tensor(embed_dim, embed_dim))
self.k_proj_weight = Parameter(torch.Tensor(embed_dim, self.kdim))
self.v_proj_weight = Parameter(torch.Tensor(embed_dim, self.vdim))
self.register_parameter('in_proj_weight', None)
else:
self.in_proj_weight = Parameter(torch.empty(3 * embed_dim, embed_dim))
self.register_parameter('q_proj_weight', None)
self.register_parameter('k_proj_weight', None)
self.register_parameter('v_proj_weight', None)
if bias:
self.in_proj_bias = Parameter(torch.empty(3 * embed_dim))
else:
self.register_parameter('in_proj_bias', None)
self.out_proj = _LinearWithBias(embed_dim, embed_dim)
if add_bias_kv:
self.bias_k = Parameter(torch.empty(1, 1, embed_dim))
self.bias_v = Parameter(torch.empty(1, 1, embed_dim))
else:
self.bias_k = self.bias_v = None
self.add_zero_attn = add_zero_attn
self._reset_parameters()
def _reset_parameters(self):
if self._qkv_same_embed_dim:
xavier_uniform_(self.in_proj_weight)
else:
xavier_uniform_(self.q_proj_weight)
xavier_uniform_(self.k_proj_weight)
xavier_uniform_(self.v_proj_weight)
if self.in_proj_bias is not None:
constant_(self.in_proj_bias, 0.)
constant_(self.out_proj.bias, 0.)
if self.bias_k is not None:
xavier_normal_(self.bias_k)
if self.bias_v is not None:
xavier_normal_(self.bias_v)
def __setstate__(self, state):
# Support loading old MultiheadAttention checkpoints generated by v1.1.0
if '_qkv_same_embed_dim' not in state:
state['_qkv_same_embed_dim'] = True
super(MultiheadAttention, self).__setstate__(state)
def forward(self, query, key, value, key_padding_mask=None,
need_weights=True, attn_mask=None):
# type: (Tensor, Tensor, Tensor, Optional[Tensor], bool, Optional[Tensor]) -> Tuple[Tensor, Optional[Tensor]]
r"""
Args:
query, key, value: map a query and a set of key-value pairs to an output.
See "Attention Is All You Need" for more details.
key_padding_mask: if provided, specified padding elements in the key will
be ignored by the attention. When given a binary mask and a value is True,
the corresponding value on the attention layer will be ignored. When given
a byte mask and a value is non-zero, the corresponding value on the attention
layer will be ignored
need_weights: output attn_output_weights.
attn_mask: 2D or 3D mask that prevents attention to certain positions. A 2D mask will be broadcasted for all
the batches while a 3D mask allows to specify a different mask for the entries of each batch.
Shape:
- Inputs:
- query: :math:`(L, N, E)` where L is the target sequence length, N is the batch size, E is
the embedding dimension.
- key: :math:`(S, N, E)`, where S is the source sequence length, N is the batch size, E is
the embedding dimension.
- value: :math:`(S, N, E)` where S is the source sequence length, N is the batch size, E is
the embedding dimension.
- key_padding_mask: :math:`(N, S)` where N is the batch size, S is the source sequence length.
If a ByteTensor is provided, the non-zero positions will be ignored while the position
with the zero positions will be unchanged. If a BoolTensor is provided, the positions with the
value of ``True`` will be ignored while the position with the value of ``False`` will be unchanged.
- attn_mask: 2D mask :math:`(L, S)` where L is the target sequence length, S is the source sequence length.
3D mask :math:`(N*num_heads, L, S)` where N is the batch size, L is the target sequence length,
S is the source sequence length. attn_mask ensure that position i is allowed to attend the unmasked
positions. If a ByteTensor is provided, the non-zero positions are not allowed to attend
while the zero positions will be unchanged. If a BoolTensor is provided, positions with ``True``
is not allowed to attend while ``False`` values will be unchanged. If a FloatTensor
is provided, it will be added to the attention weight.
- Outputs:
- attn_output: :math:`(L, N, E)` where L is the target sequence length, N is the batch size,
E is the embedding dimension.
- attn_output_weights: :math:`(N, L, S)` where N is the batch size,
L is the target sequence length, S is the source sequence length.
"""
if not self._qkv_same_embed_dim:
return F.multi_head_attention_forward(
query, key, value, self.embed_dim, self.num_heads,
self.in_proj_weight, self.in_proj_bias,
self.bias_k, self.bias_v, self.add_zero_attn,
self.dropout, self.out_proj.weight, self.out_proj.bias,
training=self.training,
key_padding_mask=key_padding_mask, need_weights=need_weights,
attn_mask=attn_mask, use_separate_proj_weight=True,
q_proj_weight=self.q_proj_weight, k_proj_weight=self.k_proj_weight,
v_proj_weight=self.v_proj_weight)
else:
return F.multi_head_attention_forward(
query, key, value, self.embed_dim, self.num_heads,
self.in_proj_weight, self.in_proj_bias,
self.bias_k, self.bias_v, self.add_zero_attn,
self.dropout, self.out_proj.weight, self.out_proj.bias,
training=self.training,
key_padding_mask=key_padding_mask, need_weights=need_weights,
attn_mask=attn_mask)
此博客为个人学习笔记,如有错误,欢迎指正!感谢各位大佬!