in fairseq/modules/multihead_attention.py [0:0]
def forward(self, query, key, value, key_padding_mask=None, incremental_state=None,
need_weights=True, static_kv=False, attn_mask=None):
"""Input shape: Time x Batch x Channel
Timesteps can be masked by supplying a T x T mask in the
`attn_mask` argument. Padding elements can be excluded from
the key by passing a binary ByteTensor (`key_padding_mask`) with shape:
batch x src_len, where padding elements are indicated by 1s.
"""
tgt_len, bsz, embed_dim = query.size()
assert embed_dim == self.embed_dim
assert list(query.size()) == [tgt_len, bsz, embed_dim]
if self.enable_torch_version and not self.onnx_trace and incremental_state is None and not static_kv:
if self.qkv_same_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,
self.training, key_padding_mask, need_weights,
attn_mask)
else:
return F.multi_head_attention_forward(query, key, value,
self.embed_dim, self.num_heads,
torch.empty([0]),
self.in_proj_bias, self.bias_k, self.bias_v,
self.add_zero_attn, self.dropout,
self.out_proj.weight, self.out_proj.bias,
self.training, key_padding_mask, need_weights,
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)
if incremental_state is not None:
saved_state = self._get_input_buffer(incremental_state)
if 'prev_key' in saved_state:
# previous time steps are cached - no need to recompute
# key and value if they are static
if static_kv:
assert self.encoder_decoder_attention and not self.self_attention
key = value = None
else:
saved_state = None
if self.self_attention:
# self-attention
q, k, v = self.in_proj_qkv(query)
elif self.encoder_decoder_attention:
# encoder-decoder attention
q = self.in_proj_q(query)
if key is None:
assert value is None
k = v = None
else:
k = self.in_proj_k(key)
v = self.in_proj_v(key)
else:
q = self.in_proj_q(query)
k = self.in_proj_k(key)
v = self.in_proj_v(value)
q *= self.scaling
if self.bias_k is not None:
assert self.bias_v is not None
k = torch.cat([k, self.bias_k.repeat(1, bsz, 1)])
v = torch.cat([v, self.bias_v.repeat(1, bsz, 1)])
if attn_mask is not None:
attn_mask = torch.cat([attn_mask, attn_mask.new_zeros(attn_mask.size(0), 1)], dim=1)
if key_padding_mask is not None:
key_padding_mask = torch.cat(
[key_padding_mask, key_padding_mask.new_zeros(key_padding_mask.size(0), 1)], dim=1)
q = q.contiguous().view(tgt_len, bsz * self.num_heads, self.head_dim).transpose(0, 1)
if k is not None:
k = k.contiguous().view(-1, bsz * self.num_heads, self.head_dim).transpose(0, 1)
if v is not None:
v = v.contiguous().view(-1, bsz * self.num_heads, self.head_dim).transpose(0, 1)
if saved_state is not None:
# saved states are stored with shape (bsz, num_heads, seq_len, head_dim)
if 'prev_key' in saved_state:
prev_key = saved_state['prev_key'].view(bsz * self.num_heads, -1, self.head_dim)
if static_kv:
k = prev_key
else:
k = torch.cat((prev_key, k), dim=1)
if 'prev_value' in saved_state:
prev_value = saved_state['prev_value'].view(bsz * self.num_heads, -1, self.head_dim)
if static_kv:
v = prev_value
else:
v = torch.cat((prev_value, v), dim=1)
saved_state['prev_key'] = k.view(bsz, self.num_heads, -1, self.head_dim)
saved_state['prev_value'] = v.view(bsz, self.num_heads, -1, self.head_dim)
self._set_input_buffer(incremental_state, saved_state)
src_len = k.size(1)
# This is part of a workaround to get around fork/join parallelism
# not supporting Optional types.
if key_padding_mask is not None and key_padding_mask.shape == torch.Size([]):
key_padding_mask = None
if key_padding_mask is not None:
assert key_padding_mask.size(0) == bsz
assert key_padding_mask.size(1) == src_len
if self.add_zero_attn:
src_len += 1
k = torch.cat([k, k.new_zeros((k.size(0), 1) + k.size()[2:])], dim=1)
v = torch.cat([v, v.new_zeros((v.size(0), 1) + v.size()[2:])], dim=1)
if attn_mask is not None:
attn_mask = torch.cat([attn_mask, attn_mask.new_zeros(attn_mask.size(0), 1)], dim=1)
if key_padding_mask is not None:
key_padding_mask = torch.cat(
[key_padding_mask, torch.zeros(key_padding_mask.size(0), 1).type_as(key_padding_mask)], dim=1)
attn_weights = torch.bmm(q, k.transpose(1, 2))
attn_weights = self.apply_sparse_mask(attn_weights, tgt_len, src_len, bsz)
assert list(attn_weights.size()) == [bsz * self.num_heads, tgt_len, src_len]
if attn_mask is not None:
attn_mask = attn_mask.unsqueeze(0)
if self.onnx_trace:
attn_mask = attn_mask.repeat(attn_weights.size(0), 1, 1)
attn_weights += attn_mask
if key_padding_mask is not None:
# don't attend to padding symbols
attn_weights = attn_weights.view(bsz, self.num_heads, tgt_len, src_len)
if self.onnx_trace:
attn_weights = torch.where(
key_padding_mask.unsqueeze(1).unsqueeze(2),
torch.Tensor([float("-Inf")]),
attn_weights.float()
).type_as(attn_weights)
else:
attn_weights = attn_weights.masked_fill(
key_padding_mask.unsqueeze(1).unsqueeze(2),
float('-inf'),
)
attn_weights = attn_weights.view(bsz * self.num_heads, tgt_len, src_len)
attn_weights = utils.softmax(
attn_weights, dim=-1, onnx_trace=self.onnx_trace,
).type_as(attn_weights)
attn_weights = F.dropout(attn_weights, p=self.dropout, training=self.training)
attn = torch.bmm(attn_weights, v)
assert list(attn.size()) == [bsz * self.num_heads, tgt_len, self.head_dim]
if (self.onnx_trace and attn.size(1) == 1):
# when ONNX tracing a single decoder step (sequence length == 1)
# the transpose is a no-op copy before view, thus unnecessary
attn = attn.contiguous().view(tgt_len, bsz, embed_dim)
else:
attn = attn.transpose(0, 1).contiguous().view(tgt_len, bsz, embed_dim)
attn = self.out_proj(attn)
if need_weights:
# average attention weights over heads
attn_weights = attn_weights.view(bsz, self.num_heads, tgt_len, src_len)
attn_weights = attn_weights.sum(dim=1) / self.num_heads
else:
attn_weights = None
return attn, attn_weights