반응형
register_hook을 사용하여 Transformer 내부의 Attention matrix(Torch.Tensor)의 gradient 받아오기
모델의 파라미터에 대한 grad가 아닌, Tensor object에 대한 grad는 계산만하고 날라가버린다. 즉, loss.backward()를 통해 backpropagation을 진행하면 중간 연산에 필요한 Tensor 변수의 gradient는 .grad로 저장이 안되고 계산이 끝나면 날라간다는 말이다. 따라서 Tensor object에 register_hook 함수로 gradient를 한번 붙잡아야 한다. 붙잡는다는 말은 gradient가 계산되었을 때, 날라가도록 두는게 아니라 다른 변수에 저장해야 한다는 말이다.
나는 중간 연산의 Tensor object에 가해지는 gradient값이 필요했다.
Transformer의 Query와 Key의 행렬곱을 통해 attention matrix를 얻는데, backpropagation과정에서 attention matrix에 대한 gradient를 얻는 방법을 공유하려고 한다.
Transformer는 Torch 내부 class인 MultiheadAttention을 사용하여 구현되는데, 이 내부 코드를 수정해줘야 한다.
Torch 내부 코드를 수정하기가 껄끄러우면, MultiheadAttention class와 이 class가 실행되기 위해 필요한 함수들을 따로 utils.py로 옮겨서 utils.MultiheadAttention class로 Transformer 구조를 변경해주면 된다. 즉, Torch의 class를 사용하는게 아니라 Torch의 class와 동일하지만, util에서 class를 꺼내서 사용하는 것이다.
Torch의 MultiheadAttention class를 살펴보면 F.multi_head_attention_forward 함수가 실행되고
F.multi_head_attention_forward 내부에는 _scaled_dot_product_attention 함수를 통해 attention matrix가 계산된다.
attention matrix가 계산되는 함수 내부까지 내려가서 attention matrix에 register_hook을 걸어줘야 한다.
# _scaled_dot_product_attention 함수 내부
B, Nt, E = q.shape
q = q / math.sqrt(E)
# (B, Nt, E) x (B, E, Ns) -> (B, Nt, Ns)
attn = torch.bmm(q, k.transpose(-2, -1))
self.save_attn_map(attn) # modified
if attn_mask is not None:
attn += attn_mask
attn = softmax(attn, dim=-1)
if dropout_p > 0.0:
attn = dropout(attn, p=dropout_p)
# (B, Nt, Ns) x (B, Ns, E) -> (B, Nt, E)
output = torch.bmm(attn, v)
gradient_hook = attn.register_hook(self.save_attn_gradient)
def save_attn_gradient(self, gradient): # modified
gradient = gradient.view(self.bsz, self.num_heads, self.tgt_len, self.src_len)
gradient = gradient.sum(dim=1) / self.num_heads
self.attention_map_gradients = gradientTorch.Tensor 변수에 register_hook을 걸어두면 gradient 값만을 받아올 수 있다. gradient값을 받아와서 self.attention_map_gradients에 gradient 값을 저장하는 함수를 register_hook에 넣어줬당
self 인자를 사용하려면 class 내부에 _scaled_dot_product_attention 함수가 존재해야 하는데, Torch 내부 함수는 class 내부에 함수가 구현되지 않아서 나는 util.py 폴더에 Multi_head_attention class 내부에 _scaled_dot_product_attention 함수를 넣어줬다.
나는 attention map도 받아오는게 필요해서 다음의 함수도 class 내부에 넣어줬고, attention map과 attention map의 gradient를 받아오는 함수도 class 내부에 넣어줬당
def save_attn_map(self, attn):
attn = attn.view(self.bsz, self.num_heads, self.tgt_len, self.src_len)
attn = attn.sum(dim=1) / self.num_heads
self.attention_map = attn
def get_attn_map(self):
return self.attention_map
def get_attn_gradients(self):
return self.attention_map_gradients
그러면 어떻게 attention map와 attention map의 gradient를 받아오냐면, Transformer 모델의 Multi_head_attention class에 접근해서 get_attn_map과 get_attn_gradients 함수를 실행해주면 된다.
attention_map 정보는 forward를 통해 저장되고, attention_map의 gradient는 loss.backward를 실행하면 Multi_head_attention class 내부의 self.attention_map_gradient 변수에 gradient가 저장된다.
for blk in clip_model.model.transformer.resblocks:
cam = blk.attn.get_attn_map()
gradients = blk.attn.get_attn_gradients()
# gradients = blk.get_attn_gradients()
print(cam.shape)
print(gradients.shape)
break
전체 코드
class MHA(Module):
r"""Allows the model to jointly attend to information
from different representation subspaces.
See `Attention Is All You Need <https://arxiv.org/abs/1706.03762>`_.
.. math::
\text{MultiHead}(Q, K, V) = \text{Concat}(head_1,\dots,head_h)W^O
where :math:`head_i = \text{Attention}(QW_i^Q, KW_i^K, VW_i^V)`.
Args:
embed_dim: Total dimension of the model.
num_heads: Number of parallel attention heads. Note that ``embed_dim`` will be split
across ``num_heads`` (i.e. each head will have dimension ``embed_dim // num_heads``).
dropout: Dropout probability on ``attn_output_weights``. Default: ``0.0`` (no dropout).
bias: If specified, adds bias to input / output projection layers. Default: ``True``.
add_bias_kv: If specified, adds bias to the key and value sequences at dim=0. Default: ``False``.
add_zero_attn: If specified, adds a new batch of zeros to the key and value sequences at dim=1.
Default: ``False``.
kdim: Total number of features for keys. Default: ``None`` (uses ``kdim=embed_dim``).
vdim: Total number of features for values. Default: ``None`` (uses ``vdim=embed_dim``).
batch_first: If ``True``, then the input and output tensors are provided
as (batch, seq, feature). Default: ``False`` (seq, batch, feature).
Examples::
>>> multihead_attn = nn.MultiheadAttention(embed_dim, num_heads)
>>> attn_output, attn_output_weights = multihead_attn(query, key, value)
"""
__constants__ = ['batch_first']
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, batch_first=False, device=None, dtype=None) -> None:
factory_kwargs = {'device': device, 'dtype': dtype}
super(MHA, 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.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"
if self._qkv_same_embed_dim is False:
self.q_proj_weight = Parameter(torch.empty((embed_dim, embed_dim), **factory_kwargs))
self.k_proj_weight = Parameter(torch.empty((embed_dim, self.kdim), **factory_kwargs))
self.v_proj_weight = Parameter(torch.empty((embed_dim, self.vdim), **factory_kwargs))
self.register_parameter('in_proj_weight', None)
else:
self.in_proj_weight = Parameter(torch.empty((3 * embed_dim, embed_dim), **factory_kwargs))
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, **factory_kwargs))
else:
self.register_parameter('in_proj_bias', None)
self.out_proj = NonDynamicallyQuantizableLinear(embed_dim, embed_dim, bias=bias, **factory_kwargs)
if add_bias_kv:
self.bias_k = Parameter(torch.empty((1, 1, embed_dim), **factory_kwargs))
self.bias_v = Parameter(torch.empty((1, 1, embed_dim), **factory_kwargs))
else:
self.bias_k = self.bias_v = None
self.add_zero_attn = add_zero_attn
self._reset_parameters()
self.attention_map = None
self.attention_map_gradients = None
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(MHA, self).__setstate__(state)
def forward(self, query: Tensor, key: Tensor, value: Tensor, key_padding_mask: Optional[Tensor] = None,
need_weights: bool = True, attn_mask: Optional[Tensor] = None) -> Tuple[Tensor, Optional[Tensor]]:
r"""
Args:
query: Query embeddings of shape :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, 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, 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"). 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 byte mask, a non-zero value indicates that the corresponding ``key``
value will be ignored.
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.
Outputs:
- **attn_output** - Attention outputs of shape :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** - Attention output weights of shape :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. Only returned
when ``need_weights=True``.
"""
if self.batch_first:
query, key, value = [x.transpose(1, 0) for x in (query, key, value)]
if not self._qkv_same_embed_dim:
attn_output, attn_output_weights = self.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:
attn_output, attn_output_weights = self.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)
if self.batch_first:
return attn_output.transpose(1, 0), attn_output_weights
else:
return attn_output, attn_output_weights
def multi_head_attention_forward(self,
query: Tensor,
key: Tensor,
value: Tensor,
embed_dim_to_check: int,
num_heads: int,
in_proj_weight: Tensor,
in_proj_bias: Optional[Tensor],
bias_k: Optional[Tensor],
bias_v: Optional[Tensor],
add_zero_attn: bool,
dropout_p: float,
out_proj_weight: Tensor,
out_proj_bias: Optional[Tensor],
training: bool = True,
key_padding_mask: Optional[Tensor] = None,
need_weights: bool = True,
attn_mask: Optional[Tensor] = None,
use_separate_proj_weight: bool = False,
q_proj_weight: Optional[Tensor] = None,
k_proj_weight: Optional[Tensor] = None,
v_proj_weight: Optional[Tensor] = None,
static_k: Optional[Tensor] = None,
static_v: Optional[Tensor] = None,
) -> 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.
embed_dim_to_check: total dimension of the model.
num_heads: parallel attention heads.
in_proj_weight, in_proj_bias: input projection weight and bias.
bias_k, bias_v: bias of the key and value sequences to be added at dim=0.
add_zero_attn: add a new batch of zeros to the key and
value sequences at dim=1.
dropout_p: probability of an element to be zeroed.
out_proj_weight, out_proj_bias: the output projection weight and bias.
training: apply dropout if is ``True``.
key_padding_mask: if provided, specified padding elements in the key will
be ignored by the attention. This is an binary mask. When the value is True,
the corresponding value on the attention layer will be filled with -inf.
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.
use_separate_proj_weight: the function accept the proj. weights for query, key,
and value in different forms. If false, in_proj_weight will be used, which is
a combination of q_proj_weight, k_proj_weight, v_proj_weight.
q_proj_weight, k_proj_weight, v_proj_weight, in_proj_bias: input projection weight and bias.
static_k, static_v: static key and value used for attention operators.
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 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 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.
- static_k: :math:`(N*num_heads, S, E/num_heads)`, where S is the source sequence length,
N is the batch size, E is the embedding dimension. E/num_heads is the head dimension.
- static_v: :math:`(N*num_heads, S, E/num_heads)`, where S is the source sequence length,
N is the batch size, E is the embedding dimension. E/num_heads is the head dimension.
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.
"""
# set up shape vars
tgt_len, bsz, embed_dim = query.shape
self.tgt_len, self.bsz, self.embed_dim = tgt_len, bsz, embed_dim
src_len, _, _ = key.shape
self.src_len = src_len
assert embed_dim == embed_dim_to_check, \
f"was expecting embedding dimension of {embed_dim_to_check}, but got {embed_dim}"
if isinstance(embed_dim, torch.Tensor):
# embed_dim can be a tensor when JIT tracing
head_dim = embed_dim.div(num_heads, rounding_mode='trunc')
else:
head_dim = embed_dim // num_heads
assert head_dim * num_heads == embed_dim, f"embed_dim {embed_dim} not divisible by num_heads {num_heads}"
if use_separate_proj_weight:
# allow MHA to have different embedding dimensions when separate projection weights are used
assert key.shape[:2] == value.shape[:2], \
f"key's sequence and batch dims {key.shape[:2]} do not match value's {value.shape[:2]}"
else:
assert key.shape == value.shape, f"key shape {key.shape} does not match value shape {value.shape}"
#
# compute in-projection
#
if not use_separate_proj_weight:
q, k, v = _in_projection_packed(query, key, value, in_proj_weight, in_proj_bias)
else:
assert q_proj_weight is not None, "use_separate_proj_weight is True but q_proj_weight is None"
assert k_proj_weight is not None, "use_separate_proj_weight is True but k_proj_weight is None"
assert v_proj_weight is not None, "use_separate_proj_weight is True but v_proj_weight is None"
if in_proj_bias is None:
b_q = b_k = b_v = None
else:
b_q, b_k, b_v = in_proj_bias.chunk(3)
q, k, v = _in_projection(query, key, value, q_proj_weight, k_proj_weight, v_proj_weight, b_q, b_k, b_v)
# prep attention mask
if attn_mask is not None:
if attn_mask.dtype == torch.uint8:
warnings.warn("Byte tensor for attn_mask in nn.MultiheadAttention is deprecated. Use bool tensor instead.")
attn_mask = attn_mask.to(torch.bool)
else:
assert attn_mask.is_floating_point() or attn_mask.dtype == torch.bool, \
f"Only float, byte, and bool types are supported for attn_mask, not {attn_mask.dtype}"
# ensure attn_mask's dim is 3
if attn_mask.dim() == 2:
correct_2d_size = (tgt_len, src_len)
if attn_mask.shape != correct_2d_size:
raise RuntimeError(f"The shape of the 2D attn_mask is {attn_mask.shape}, but should be {correct_2d_size}.")
attn_mask = attn_mask.unsqueeze(0)
elif attn_mask.dim() == 3:
correct_3d_size = (bsz * num_heads, tgt_len, src_len)
if attn_mask.shape != correct_3d_size:
raise RuntimeError(f"The shape of the 3D attn_mask is {attn_mask.shape}, but should be {correct_3d_size}.")
else:
raise RuntimeError(f"attn_mask's dimension {attn_mask.dim()} is not supported")
# prep key padding mask
if key_padding_mask is not None and key_padding_mask.dtype == torch.uint8:
warnings.warn("Byte tensor for key_padding_mask in nn.MultiheadAttention is deprecated. Use bool tensor instead.")
key_padding_mask = key_padding_mask.to(torch.bool)
# add bias along batch dimension (currently second)
if bias_k is not None and bias_v is not None:
assert static_k is None, "bias cannot be added to static key."
assert static_v is None, "bias cannot be added to static value."
k = torch.cat([k, bias_k.repeat(1, bsz, 1)])
v = torch.cat([v, bias_v.repeat(1, bsz, 1)])
if attn_mask is not None:
attn_mask = pad(attn_mask, (0, 1))
if key_padding_mask is not None:
key_padding_mask = pad(key_padding_mask, (0, 1))
else:
assert bias_k is None
assert bias_v is None
#
# reshape q, k, v for multihead attention and make em batch first
#
q = q.contiguous().view(tgt_len, bsz * num_heads, head_dim).transpose(0, 1)
if static_k is None:
k = k.contiguous().view(k.shape[0], bsz * num_heads, head_dim).transpose(0, 1)
else:
# TODO finish disentangling control flow so we don't do in-projections when statics are passed
assert static_k.size(0) == bsz * num_heads, \
f"expecting static_k.size(0) of {bsz * num_heads}, but got {static_k.size(0)}"
assert static_k.size(2) == head_dim, \
f"expecting static_k.size(2) of {head_dim}, but got {static_k.size(2)}"
k = static_k
if static_v is None:
v = v.contiguous().view(v.shape[0], bsz * num_heads, head_dim).transpose(0, 1)
else:
# TODO finish disentangling control flow so we don't do in-projections when statics are passed
assert static_v.size(0) == bsz * num_heads, \
f"expecting static_v.size(0) of {bsz * num_heads}, but got {static_v.size(0)}"
assert static_v.size(2) == head_dim, \
f"expecting static_v.size(2) of {head_dim}, but got {static_v.size(2)}"
v = static_v
# add zero attention along batch dimension (now first)
if add_zero_attn:
zero_attn_shape = (bsz * num_heads, 1, head_dim)
k = torch.cat([k, torch.zeros(zero_attn_shape, dtype=k.dtype, device=k.device)], dim=1)
v = torch.cat([v, torch.zeros(zero_attn_shape, dtype=v.dtype, device=v.device)], dim=1)
if attn_mask is not None:
attn_mask = pad(attn_mask, (0, 1))
if key_padding_mask is not None:
key_padding_mask = pad(key_padding_mask, (0, 1))
# update source sequence length after adjustments
src_len = k.size(1)
# merge key padding and attention masks
if key_padding_mask is not None:
assert key_padding_mask.shape == (bsz, src_len), \
f"expecting key_padding_mask shape of {(bsz, src_len)}, but got {key_padding_mask.shape}"
key_padding_mask = key_padding_mask.view(bsz, 1, 1, src_len). \
expand(-1, num_heads, -1, -1).reshape(bsz * num_heads, 1, src_len)
if attn_mask is None:
attn_mask = key_padding_mask
elif attn_mask.dtype == torch.bool:
attn_mask = attn_mask.logical_or(key_padding_mask)
else:
attn_mask = attn_mask.masked_fill(key_padding_mask, float("-inf"))
# convert mask to float
if attn_mask is not None and attn_mask.dtype == torch.bool:
new_attn_mask = torch.zeros_like(attn_mask, dtype=torch.float)
new_attn_mask.masked_fill_(attn_mask, float("-inf"))
attn_mask = new_attn_mask
# adjust dropout probability
if not training:
dropout_p = 0.0
#
# (deep breath) calculate attention and out projection
#
attn_output, attn_output_weights = self._scaled_dot_product_attention(q, k, v, attn_mask, dropout_p)
attn_output = attn_output.transpose(0, 1).contiguous().view(tgt_len, bsz, embed_dim)
attn_output = linear(attn_output, out_proj_weight, out_proj_bias)
if need_weights:
# average attention weights over heads
attn_output_weights = attn_output_weights.view(bsz, num_heads, tgt_len, src_len)
return attn_output, attn_output_weights.sum(dim=1) / num_heads
else:
return attn_output, None
def _scaled_dot_product_attention(self,
q: Tensor,
k: Tensor,
v: Tensor,
attn_mask: Optional[Tensor] = None,
dropout_p: float = 0.0,
) -> Tuple[Tensor, Tensor]:
r"""
Computes scaled dot product attention on query, key and value tensors, using
an optional attention mask if passed, and applying dropout if a probability
greater than 0.0 is specified.
Returns a tensor pair containing attended values and attention weights.
Args:
q, k, v: query, key and value tensors. See Shape section for shape details.
attn_mask: optional tensor containing mask values to be added to calculated
attention. May be 2D or 3D; see Shape section for details.
dropout_p: dropout probability. If greater than 0.0, dropout is applied.
Shape:
- q: :math:`(B, Nt, E)` where B is batch size, Nt is the target sequence length,
and E is embedding dimension.
- key: :math:`(B, Ns, E)` where B is batch size, Ns is the source sequence length,
and E is embedding dimension.
- value: :math:`(B, Ns, E)` where B is batch size, Ns is the source sequence length,
and E is embedding dimension.
- attn_mask: either a 3D tensor of shape :math:`(B, Nt, Ns)` or a 2D tensor of
shape :math:`(Nt, Ns)`.
- Output: attention values have shape :math:`(B, Nt, E)`; attention weights
have shape :math:`(B, Nt, Ns)`
"""
B, Nt, E = q.shape
q = q / math.sqrt(E)
# (B, Nt, E) x (B, E, Ns) -> (B, Nt, Ns)
attn = torch.bmm(q, k.transpose(-2, -1))
self.save_attn_map(attn) # modified
if attn_mask is not None:
attn += attn_mask
attn = softmax(attn, dim=-1)
if dropout_p > 0.0:
attn = dropout(attn, p=dropout_p)
# (B, Nt, Ns) x (B, Ns, E) -> (B, Nt, E)
output = torch.bmm(attn, v)
gradient_hook = attn.register_hook(self.save_attn_gradient) # modified
# print(attn_gradients)
# print(attn_gradients, 'attn_gradients')
# print(attn.grad, ' attn.grad')
# print(attn_gradients, 'attn_gradients')
return output, attn
def save_attn_gradient(self, gradient): # modified
gradient = gradient.view(self.bsz, self.num_heads, self.tgt_len, self.src_len)
gradient = gradient.sum(dim=1) / self.num_heads
self.attention_map_gradients = gradient
def save_attn_map(self, attn):
attn = attn.view(self.bsz, self.num_heads, self.tgt_len, self.src_len)
attn = attn.sum(dim=1) / self.num_heads
self.attention_map = attn
def get_attn_map(self):
return self.attention_map
def get_attn_gradients(self):
return self.attention_map_gradients
def _in_projection_packed(
q: Tensor,
k: Tensor,
v: Tensor,
w: Tensor,
b: Optional[Tensor] = None,
) -> List[Tensor]:
r"""
Performs the in-projection step of the attention operation, using packed weights.
Output is a triple containing projection tensors for query, key and value.
Args:
q, k, v: query, key and value tensors to be projected. For self-attention,
these are typically the same tensor; for encoder-decoder attention,
k and v are typically the same tensor. (We take advantage of these
identities for performance if they are present.) Regardless, q, k and v
must share a common embedding dimension; otherwise their shapes may vary.
w: projection weights for q, k and v, packed into a single tensor. Weights
are packed along dimension 0, in q, k, v order.
b: optional projection biases for q, k and v, packed into a single tensor
in q, k, v order.
Shape:
Inputs:
- q: :math:`(..., E)` where E is the embedding dimension
- k: :math:`(..., E)` where E is the embedding dimension
- v: :math:`(..., E)` where E is the embedding dimension
- w: :math:`(E * 3, E)` where E is the embedding dimension
- b: :math:`E * 3` where E is the embedding dimension
Output:
- in output list :math:`[q', k', v']`, each output tensor will have the
same shape as the corresponding input tensor.
"""
E = q.size(-1)
if k is v:
if q is k:
# self-attention
return linear(q, w, b).chunk(3, dim=-1)
else:
# encoder-decoder attention
w_q, w_kv = w.split([E, E * 2])
if b is None:
b_q = b_kv = None
else:
b_q, b_kv = b.split([E, E * 2])
return (linear(q, w_q, b_q),) + linear(k, w_kv, b_kv).chunk(2, dim=-1)
else:
w_q, w_k, w_v = w.chunk(3)
if b is None:
b_q = b_k = b_v = None
else:
b_q, b_k, b_v = b.chunk(3)
return linear(q, w_q, b_q), linear(k, w_k, b_k), linear(v, w_v, b_v)
def _in_projection(
q: Tensor,
k: Tensor,
v: Tensor,
w_q: Tensor,
w_k: Tensor,
w_v: Tensor,
b_q: Optional[Tensor] = None,
b_k: Optional[Tensor] = None,
b_v: Optional[Tensor] = None,
) -> Tuple[Tensor, Tensor, Tensor]:
r"""
Performs the in-projection step of the attention operation. This is simply
a triple of linear projections, with shape constraints on the weights which
ensure embedding dimension uniformity in the projected outputs.
Output is a triple containing projection tensors for query, key and value.
Args:
q, k, v: query, key and value tensors to be projected.
w_q, w_k, w_v: weights for q, k and v, respectively.
b_q, b_k, b_v: optional biases for q, k and v, respectively.
Shape:
Inputs:
- q: :math:`(Qdims..., Eq)` where Eq is the query embedding dimension and Qdims are any
number of leading dimensions.
- k: :math:`(Kdims..., Ek)` where Ek is the key embedding dimension and Kdims are any
number of leading dimensions.
- v: :math:`(Vdims..., Ev)` where Ev is the value embedding dimension and Vdims are any
number of leading dimensions.
- w_q: :math:`(Eq, Eq)`
- w_k: :math:`(Eq, Ek)`
- w_v: :math:`(Eq, Ev)`
- b_q: :math:`(Eq)`
- b_k: :math:`(Eq)`
- b_v: :math:`(Eq)`
Output: in output triple :math:`(q', k', v')`,
- q': :math:`[Qdims..., Eq]`
- k': :math:`[Kdims..., Eq]`
- v': :math:`[Vdims..., Eq]`
"""
Eq, Ek, Ev = q.size(-1), k.size(-1), v.size(-1)
assert w_q.shape == (Eq, Eq), f"expecting query weights shape of {(Eq, Eq)}, but got {w_q.shape}"
assert w_k.shape == (Eq, Ek), f"expecting key weights shape of {(Eq, Ek)}, but got {w_k.shape}"
assert w_v.shape == (Eq, Ev), f"expecting value weights shape of {(Eq, Ev)}, but got {w_v.shape}"
assert b_q is None or b_q.shape == (Eq,), f"expecting query bias shape of {(Eq,)}, but got {b_q.shape}"
assert b_k is None or b_k.shape == (Eq,), f"expecting key bias shape of {(Eq,)}, but got {b_k.shape}"
assert b_v is None or b_v.shape == (Eq,), f"expecting value bias shape of {(Eq,)}, but got {b_v.shape}"
return linear(q, w_q, b_q), linear(k, w_k, b_k), linear(v, w_v, b_v)
def linear(input: Tensor, weight: Tensor, bias: Optional[Tensor] = None) -> Tensor:
r"""
Applies a linear transformation to the incoming data: :math:`y = xA^T + b`.
This operator supports :ref:`TensorFloat32<tf32_on_ampere>`.
Shape:
- Input: :math:`(N, *, in\_features)` N is the batch size, `*` means any number of
additional dimensions
- Weight: :math:`(out\_features, in\_features)`
- Bias: :math:`(out\_features)`
- Output: :math:`(N, *, out\_features)`
"""
if has_torch_function_variadic(input, weight, bias):
return handle_torch_function(linear, (input, weight, bias), input, weight, bias=bias)
return torch._C._nn.linear(input, weight, bias)
반응형
'Python > PyTorch 공부' 카테고리의 다른 글
| [PyTorch] Multi_head_attention에서 target sequence length와 source sequence length 의미 (0) | 2022.07.27 |
|---|---|
| [PyTorch] Tensor.retain_grad() (0) | 2022.07.19 |
| [Pytorch] Sementation mask 시각화 하기 (0) | 2022.06.26 |
| [Pytorch] List를 Tensor로 변경하기. torch.stack (0) | 2022.05.22 |
| [PyTorch] 학습 progress bar 설정하기 (14) | 2022.05.17 |