from typing import Optional, Tuple
import torch
from torch import Tensor
from torch.nn import Module
from torch.nn import functional as F
from torch.nn.init import constant_, xavier_normal_, xavier_uniform_
from torch.nn.parameter import Parameter
[文档]
class MultiheadAttention(Module):
r"""Allows the model to jointly attend to information
from different representation subspaces as described in the paper:
`Attention Is All You Need <https://arxiv.org/abs/1706.03762>`_.
This module is modified from the original torch.nn.MultiheadAttention
"""
__constants__ = ["batch_first"]
def __init__(
self,
embed_dim,
num_heads,
dropout=0.0,
batch_first=True,
device=None,
dtype=None,
) -> None:
factory_kwargs = {"device": device, "dtype": dtype}
super(MultiheadAttention, self).__init__()
self.embed_dim = embed_dim
self._qkv_same_embed_dim = True
self.num_heads = num_heads
self.dropout = dropout
self.batch_first = batch_first
self.head_dim = embed_dim // num_heads
assert (
self.head_dim * num_heads == self.embed_dim
), "embed_dim must be divisible by num_heads"
# an identity out_proj
self.in_proj_weight = torch.eye(embed_dim, **factory_kwargs)
self.out_proj_weight = torch.eye(embed_dim, **factory_kwargs)
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 _apply(self, fn):
self.in_proj_weight = fn(self.in_proj_weight)
self.out_proj_weight = fn(self.out_proj_weight)
return super()._apply(fn)
[文档]
def forward(
self,
query: Tensor,
key: Tensor,
value: Tensor,
key_padding_mask: Optional[Tensor] = None,
need_weights: bool = True,
attn_mask: Optional[Tensor] = None,
average_attn_weights: bool = True,
) -> Tuple[Tensor, Optional[Tensor]]:
r"""
Args:
query: Query embeddings of shape :math:`(L, E_q)` for unbatched input, :math:`(L, N, E_q)` when ``batch_first=False``
or :math:`(N, L, E_q)` when ``batch_first=True``, where :math:`L` is the target sequence length,
:math:`N` is the batch size, and :math:`E_q` is the query embedding dimension ``embed_dim``.
Queries are compared against key-value pairs to produce the output.
See "Attention Is All You Need" for more details.
key: Key embeddings of shape :math:`(S, E_k)` for unbatched input, :math:`(S, N, E_k)` when ``batch_first=False``
or :math:`(N, S, E_k)` when ``batch_first=True``, where :math:`S` is the source sequence length,
:math:`N` is the batch size, and :math:`E_k` is the key embedding dimension ``kdim``.
See "Attention Is All You Need" for more details.
value: Value embeddings of shape :math:`(S, E_v)` for unbatched input, :math:`(S, N, E_v)` when
``batch_first=False`` or :math:`(N, S, E_v)` when ``batch_first=True``, where :math:`S` is the source
sequence length, :math:`N` is the batch size, and :math:`E_v` is the value embedding dimension ``vdim``.
See "Attention Is All You Need" for more details.
key_padding_mask: If specified, a mask of shape :math:`(N, S)` indicating which elements within ``key``
to ignore for the purpose of attention (i.e. treat as "padding"). For unbatched `query`, shape should be :math:`(S)`.
Binary and byte masks are supported.
For a binary mask, a ``True`` value indicates that the corresponding ``key`` value will be ignored for
the purpose of attention. For a float mask, it will be directly added to the corresponding ``key`` value.
need_weights: If specified, returns ``attn_output_weights`` in addition to ``attn_outputs``.
Default: ``True``.
attn_mask: If specified, a 2D or 3D mask preventing attention to certain positions. Must be of shape
:math:`(L, S)` or :math:`(N\cdot\text{num\_heads}, L, S)`, where :math:`N` is the batch size,
:math:`L` is the target sequence length, and :math:`S` is the source sequence length. A 2D mask will be
broadcasted across the batch while a 3D mask allows for a different mask for each entry in the batch.
Binary, byte, and float masks are supported. For a binary mask, a ``True`` value indicates that the
corresponding position is not allowed to attend. For a byte mask, a non-zero value indicates that the
corresponding position is not allowed to attend. For a float mask, the mask values will be added to
the attention weight.
average_attn_weights: If true, indicates that the returned ``attn_weights`` should be averaged across
heads. Otherwise, ``attn_weights`` are provided separately per head. Note that this flag only has an
effect when ``need_weights=True``. Default: ``True`` (i.e. average weights across heads)
Outputs:
- **attn_output** - Attention outputs of shape :math:`(L, E)` when input is unbatched,
:math:`(L, N, E)` when ``batch_first=False`` or :math:`(N, L, E)` when ``batch_first=True``,
where :math:`L` is the target sequence length, :math:`N` is the batch size, and :math:`E` is the
embedding dimension ``embed_dim``.
- **attn_output_weights** - Only returned when ``need_weights=True``. If ``average_attn_weights=True``,
returns attention weights averaged across heads of shape :math:`(L, S)` when input is unbatched or
:math:`(N, L, S)`, where :math:`N` is the batch size, :math:`L` is the target sequence length, and
:math:`S` is the source sequence length. If ``average_attn_weights=False``, returns attention weights per
head of shape :math:`(\text{num\_heads}, L, S)` when input is unbatched or :math:`(N, \text{num\_heads}, L, S)`.
.. note::
`batch_first` argument is ignored for unbatched inputs.
"""
is_batched = query.dim() == 3
if key_padding_mask is not None:
_kpm_dtype = key_padding_mask.dtype
if _kpm_dtype != torch.bool and not torch.is_floating_point(
key_padding_mask
):
raise AssertionError(
"only bool and floating types of key_padding_mask are supported"
)
if self.batch_first and is_batched:
# make sure that the transpose op does not affect the "is" property
if key is value:
if query is key:
query = key = value = query.transpose(1, 0)
else:
query, key = [x.transpose(1, 0) for x in (query, key)]
value = key
else:
query, key, value = [x.transpose(1, 0) for x in (query, key, value)]
attn_output, attn_output_weights = F.multi_head_attention_forward(
query,
key,
value,
self.embed_dim,
self.num_heads,
in_proj_weight=None,
in_proj_bias=None,
bias_k=None,
bias_v=None,
add_zero_attn=False,
dropout_p=self.dropout,
out_proj_weight=self.out_proj_weight,
out_proj_bias=None,
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.in_proj_weight,
k_proj_weight=self.in_proj_weight,
v_proj_weight=self.in_proj_weight,
average_attn_weights=average_attn_weights,
)
if self.batch_first and is_batched:
return attn_output.transpose(1, 0), attn_output_weights
else:
return attn_output, attn_output_weights