From d80ac2fd2df4e7fb8a28acfa512bb11472b5cc99 Mon Sep 17 00:00:00 2001
From: liugz18 <57401541+liugz18@users.noreply.github.com>
Date: 星期四, 18 七月 2024 21:34:55 +0800
Subject: [PATCH] Rename 'res' in line 514 to avoid with naming conflict with line 365
---
funasr/models/transformer/attention.py | 700 +++++++++-------------------------------------------------
1 files changed, 111 insertions(+), 589 deletions(-)
diff --git a/funasr/models/transformer/attention.py b/funasr/models/transformer/attention.py
index 04607c6..6e6f754 100644
--- a/funasr/models/transformer/attention.py
+++ b/funasr/models/transformer/attention.py
@@ -15,7 +15,8 @@
import torch.nn.functional as F
from funasr.models.transformer.utils.nets_utils import make_pad_mask
-import funasr.modules.lora.layers as lora
+import funasr.models.lora.layers as lora
+
class MultiHeadedAttention(nn.Module):
"""Multi-Head Attention layer.
@@ -81,9 +82,10 @@
n_batch = value.size(0)
if mask is not None:
mask = mask.unsqueeze(1).eq(0) # (batch, 1, *, time2)
- min_value = float(
- numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min
- )
+
+ min_value = -float(
+ "inf"
+ ) # min_value = float(np.finfo(torch.tensor(0, dtype=qk.dtype).numpy().dtype).min)
scores = scores.masked_fill(mask, min_value)
self.attn = torch.softmax(scores, dim=-1).masked_fill(
mask, 0.0
@@ -116,6 +118,104 @@
q, k, v = self.forward_qkv(query, key, value)
scores = torch.matmul(q, k.transpose(-2, -1)) / math.sqrt(self.d_k)
return self.forward_attention(v, scores, mask)
+
+
+class MultiHeadedAttentionExport(nn.Module):
+ def __init__(self, model):
+ super().__init__()
+ self.d_k = model.d_k
+ self.h = model.h
+ self.linear_q = model.linear_q
+ self.linear_k = model.linear_k
+ self.linear_v = model.linear_v
+ self.linear_out = model.linear_out
+ self.attn = None
+ self.all_head_size = self.h * self.d_k
+
+ def forward(self, query, key, value, mask):
+ q, k, v = self.forward_qkv(query, key, value)
+ scores = torch.matmul(q, k.transpose(-2, -1)) / math.sqrt(self.d_k)
+ return self.forward_attention(v, scores, mask)
+
+ def transpose_for_scores(self, x: torch.Tensor) -> torch.Tensor:
+ new_x_shape = x.size()[:-1] + (self.h, self.d_k)
+ x = x.view(new_x_shape)
+ return x.permute(0, 2, 1, 3)
+
+ def forward_qkv(self, query, key, value):
+ q = self.linear_q(query)
+ k = self.linear_k(key)
+ v = self.linear_v(value)
+ q = self.transpose_for_scores(q)
+ k = self.transpose_for_scores(k)
+ v = self.transpose_for_scores(v)
+ return q, k, v
+
+ def forward_attention(self, value, scores, mask):
+ scores = scores + mask
+
+ self.attn = torch.softmax(scores, dim=-1)
+ context_layer = torch.matmul(self.attn, value) # (batch, head, time1, d_k)
+
+ context_layer = context_layer.permute(0, 2, 1, 3).contiguous()
+ new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,)
+ context_layer = context_layer.view(new_context_layer_shape)
+ return self.linear_out(context_layer) # (batch, time1, d_model)
+
+
+class RelPosMultiHeadedAttentionExport(MultiHeadedAttentionExport):
+ def __init__(self, model):
+ super().__init__(model)
+ self.linear_pos = model.linear_pos
+ self.pos_bias_u = model.pos_bias_u
+ self.pos_bias_v = model.pos_bias_v
+
+ def forward(self, query, key, value, pos_emb, mask):
+ q, k, v = self.forward_qkv(query, key, value)
+ q = q.transpose(1, 2) # (batch, time1, head, d_k)
+
+ p = self.transpose_for_scores(self.linear_pos(pos_emb)) # (batch, head, time1, d_k)
+
+ # (batch, head, time1, d_k)
+ q_with_bias_u = (q + self.pos_bias_u).transpose(1, 2)
+ # (batch, head, time1, d_k)
+ q_with_bias_v = (q + self.pos_bias_v).transpose(1, 2)
+
+ # compute attention score
+ # first compute matrix a and matrix c
+ # as described in https://arxiv.org/abs/1901.02860 Section 3.3
+ # (batch, head, time1, time2)
+ matrix_ac = torch.matmul(q_with_bias_u, k.transpose(-2, -1))
+
+ # compute matrix b and matrix d
+ # (batch, head, time1, time1)
+ matrix_bd = torch.matmul(q_with_bias_v, p.transpose(-2, -1))
+ matrix_bd = self.rel_shift(matrix_bd)
+
+ scores = (matrix_ac + matrix_bd) / math.sqrt(self.d_k) # (batch, head, time1, time2)
+
+ return self.forward_attention(v, scores, mask)
+
+ def rel_shift(self, x):
+ zero_pad = torch.zeros((*x.size()[:3], 1), device=x.device, dtype=x.dtype)
+ x_padded = torch.cat([zero_pad, x], dim=-1)
+
+ x_padded = x_padded.view(*x.size()[:2], x.size(3) + 1, x.size(2))
+ x = x_padded[:, :, 1:].view_as(x)[
+ :, :, :, : x.size(-1) // 2 + 1
+ ] # only keep the positions from 0 to time2
+ return x
+
+ def forward_attention(self, value, scores, mask):
+ scores = scores + mask
+
+ self.attn = torch.softmax(scores, dim=-1)
+ context_layer = torch.matmul(self.attn, value) # (batch, head, time1, d_k)
+
+ context_layer = context_layer.permute(0, 2, 1, 3).contiguous()
+ new_context_layer_shape = context_layer.size()[:-2] + (self.all_head_size,)
+ context_layer = context_layer.view(new_context_layer_shape)
+ return self.linear_out(context_layer) # (batch, time1, d_model)
class LegacyRelPositionMultiHeadedAttention(MultiHeadedAttention):
@@ -206,9 +306,7 @@
matrix_bd = torch.matmul(q_with_bias_v, p.transpose(-2, -1))
matrix_bd = self.rel_shift(matrix_bd)
- scores = (matrix_ac + matrix_bd) / math.sqrt(
- self.d_k
- ) # (batch, head, time1, time2)
+ scores = (matrix_ac + matrix_bd) / math.sqrt(self.d_k) # (batch, head, time1, time2)
return self.forward_attention(v, scores, mask)
@@ -258,7 +356,7 @@
x_padded = x_padded.view(*x.size()[:2], x.size(3) + 1, x.size(2))
x = x_padded[:, :, 1:].view_as(x)[
:, :, :, : x.size(-1) // 2 + 1
- ] # only keep the positions from 0 to time2
+ ] # only keep the positions from 0 to time2
if self.zero_triu:
ones = torch.ones((x.size(2), x.size(3)), device=x.device)
@@ -305,538 +403,10 @@
matrix_bd = torch.matmul(q_with_bias_v, p.transpose(-2, -1))
matrix_bd = self.rel_shift(matrix_bd)
- scores = (matrix_ac + matrix_bd) / math.sqrt(
- self.d_k
- ) # (batch, head, time1, time2)
+ scores = (matrix_ac + matrix_bd) / math.sqrt(self.d_k) # (batch, head, time1, time2)
return self.forward_attention(v, scores, mask)
-
-class MultiHeadedAttentionSANM(nn.Module):
- """Multi-Head Attention layer.
-
- Args:
- n_head (int): The number of heads.
- n_feat (int): The number of features.
- dropout_rate (float): Dropout rate.
-
- """
-
- def __init__(self, n_head, in_feat, n_feat, dropout_rate, kernel_size, sanm_shfit=0, lora_list=None, lora_rank=8, lora_alpha=16, lora_dropout=0.1):
- """Construct an MultiHeadedAttention object."""
- super(MultiHeadedAttentionSANM, self).__init__()
- assert n_feat % n_head == 0
- # We assume d_v always equals d_k
- self.d_k = n_feat // n_head
- self.h = n_head
- # self.linear_q = nn.Linear(n_feat, n_feat)
- # self.linear_k = nn.Linear(n_feat, n_feat)
- # self.linear_v = nn.Linear(n_feat, n_feat)
- if lora_list is not None:
- if "o" in lora_list:
- self.linear_out = lora.Linear(n_feat, n_feat, r=lora_rank, lora_alpha=lora_alpha, lora_dropout=lora_dropout)
- else:
- self.linear_out = nn.Linear(n_feat, n_feat)
- lora_qkv_list = ["q" in lora_list, "k" in lora_list, "v" in lora_list]
- if lora_qkv_list == [False, False, False]:
- self.linear_q_k_v = nn.Linear(in_feat, n_feat * 3)
- else:
- self.linear_q_k_v = lora.MergedLinear(in_feat, n_feat * 3, r=lora_rank, lora_alpha=lora_alpha, lora_dropout=lora_dropout, enable_lora=lora_qkv_list)
- else:
- self.linear_out = nn.Linear(n_feat, n_feat)
- self.linear_q_k_v = nn.Linear(in_feat, n_feat * 3)
- self.attn = None
- self.dropout = nn.Dropout(p=dropout_rate)
-
- self.fsmn_block = nn.Conv1d(n_feat, n_feat, kernel_size, stride=1, padding=0, groups=n_feat, bias=False)
- # padding
- left_padding = (kernel_size - 1) // 2
- if sanm_shfit > 0:
- left_padding = left_padding + sanm_shfit
- right_padding = kernel_size - 1 - left_padding
- self.pad_fn = nn.ConstantPad1d((left_padding, right_padding), 0.0)
-
- def forward_fsmn(self, inputs, mask, mask_shfit_chunk=None):
- b, t, d = inputs.size()
- if mask is not None:
- mask = torch.reshape(mask, (b, -1, 1))
- if mask_shfit_chunk is not None:
- mask = mask * mask_shfit_chunk
- inputs = inputs * mask
-
- x = inputs.transpose(1, 2)
- x = self.pad_fn(x)
- x = self.fsmn_block(x)
- x = x.transpose(1, 2)
- x += inputs
- x = self.dropout(x)
- if mask is not None:
- x = x * mask
- return x
-
- def forward_qkv(self, x):
- """Transform query, key and value.
-
- Args:
- query (torch.Tensor): Query tensor (#batch, time1, size).
- key (torch.Tensor): Key tensor (#batch, time2, size).
- value (torch.Tensor): Value tensor (#batch, time2, size).
-
- Returns:
- torch.Tensor: Transformed query tensor (#batch, n_head, time1, d_k).
- torch.Tensor: Transformed key tensor (#batch, n_head, time2, d_k).
- torch.Tensor: Transformed value tensor (#batch, n_head, time2, d_k).
-
- """
- b, t, d = x.size()
- q_k_v = self.linear_q_k_v(x)
- q, k, v = torch.split(q_k_v, int(self.h * self.d_k), dim=-1)
- q_h = torch.reshape(q, (b, t, self.h, self.d_k)).transpose(1, 2) # (batch, head, time1, d_k)
- k_h = torch.reshape(k, (b, t, self.h, self.d_k)).transpose(1, 2) # (batch, head, time2, d_k)
- v_h = torch.reshape(v, (b, t, self.h, self.d_k)).transpose(1, 2) # (batch, head, time2, d_k)
-
- return q_h, k_h, v_h, v
-
- def forward_attention(self, value, scores, mask, mask_att_chunk_encoder=None):
- """Compute attention context vector.
-
- Args:
- value (torch.Tensor): Transformed value (#batch, n_head, time2, d_k).
- scores (torch.Tensor): Attention score (#batch, n_head, time1, time2).
- mask (torch.Tensor): Mask (#batch, 1, time2) or (#batch, time1, time2).
-
- Returns:
- torch.Tensor: Transformed value (#batch, time1, d_model)
- weighted by the attention score (#batch, time1, time2).
-
- """
- n_batch = value.size(0)
- if mask is not None:
- if mask_att_chunk_encoder is not None:
- mask = mask * mask_att_chunk_encoder
-
- mask = mask.unsqueeze(1).eq(0) # (batch, 1, *, time2)
-
- min_value = float(
- numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min
- )
- scores = scores.masked_fill(mask, min_value)
- self.attn = torch.softmax(scores, dim=-1).masked_fill(
- mask, 0.0
- ) # (batch, head, time1, time2)
- else:
- self.attn = torch.softmax(scores, dim=-1) # (batch, head, time1, time2)
-
- p_attn = self.dropout(self.attn)
- x = torch.matmul(p_attn, value) # (batch, head, time1, d_k)
- x = (
- x.transpose(1, 2).contiguous().view(n_batch, -1, self.h * self.d_k)
- ) # (batch, time1, d_model)
-
- return self.linear_out(x) # (batch, time1, d_model)
-
- def forward(self, x, mask, mask_shfit_chunk=None, mask_att_chunk_encoder=None):
- """Compute scaled dot product attention.
-
- Args:
- query (torch.Tensor): Query tensor (#batch, time1, size).
- key (torch.Tensor): Key tensor (#batch, time2, size).
- value (torch.Tensor): Value tensor (#batch, time2, size).
- mask (torch.Tensor): Mask tensor (#batch, 1, time2) or
- (#batch, time1, time2).
-
- Returns:
- torch.Tensor: Output tensor (#batch, time1, d_model).
-
- """
- q_h, k_h, v_h, v = self.forward_qkv(x)
- fsmn_memory = self.forward_fsmn(v, mask, mask_shfit_chunk)
- q_h = q_h * self.d_k ** (-0.5)
- scores = torch.matmul(q_h, k_h.transpose(-2, -1))
- att_outs = self.forward_attention(v_h, scores, mask, mask_att_chunk_encoder)
- return att_outs + fsmn_memory
-
- def forward_chunk(self, x, cache=None, chunk_size=None, look_back=0):
- """Compute scaled dot product attention.
-
- Args:
- query (torch.Tensor): Query tensor (#batch, time1, size).
- key (torch.Tensor): Key tensor (#batch, time2, size).
- value (torch.Tensor): Value tensor (#batch, time2, size).
- mask (torch.Tensor): Mask tensor (#batch, 1, time2) or
- (#batch, time1, time2).
-
- Returns:
- torch.Tensor: Output tensor (#batch, time1, d_model).
-
- """
- q_h, k_h, v_h, v = self.forward_qkv(x)
- if chunk_size is not None and look_back > 0 or look_back == -1:
- if cache is not None:
- k_h_stride = k_h[:, :, :-(chunk_size[2]), :]
- v_h_stride = v_h[:, :, :-(chunk_size[2]), :]
- k_h = torch.cat((cache["k"], k_h), dim=2)
- v_h = torch.cat((cache["v"], v_h), dim=2)
-
- cache["k"] = torch.cat((cache["k"], k_h_stride), dim=2)
- cache["v"] = torch.cat((cache["v"], v_h_stride), dim=2)
- if look_back != -1:
- cache["k"] = cache["k"][:, :, -(look_back * chunk_size[1]):, :]
- cache["v"] = cache["v"][:, :, -(look_back * chunk_size[1]):, :]
- else:
- cache_tmp = {"k": k_h[:, :, :-(chunk_size[2]), :],
- "v": v_h[:, :, :-(chunk_size[2]), :]}
- cache = cache_tmp
- fsmn_memory = self.forward_fsmn(v, None)
- q_h = q_h * self.d_k ** (-0.5)
- scores = torch.matmul(q_h, k_h.transpose(-2, -1))
- att_outs = self.forward_attention(v_h, scores, None)
- return att_outs + fsmn_memory, cache
-
-
-class MultiHeadedAttentionSANMwithMask(MultiHeadedAttentionSANM):
- def __init__(self, *args, **kwargs):
- super().__init__(*args, **kwargs)
-
- def forward(self, x, mask, mask_shfit_chunk=None, mask_att_chunk_encoder=None):
- q_h, k_h, v_h, v = self.forward_qkv(x)
- fsmn_memory = self.forward_fsmn(v, mask[0], mask_shfit_chunk)
- q_h = q_h * self.d_k ** (-0.5)
- scores = torch.matmul(q_h, k_h.transpose(-2, -1))
- att_outs = self.forward_attention(v_h, scores, mask[1], mask_att_chunk_encoder)
- return att_outs + fsmn_memory
-
-class MultiHeadedAttentionSANMDecoder(nn.Module):
- """Multi-Head Attention layer.
-
- Args:
- n_head (int): The number of heads.
- n_feat (int): The number of features.
- dropout_rate (float): Dropout rate.
-
- """
-
- def __init__(self, n_feat, dropout_rate, kernel_size, sanm_shfit=0):
- """Construct an MultiHeadedAttention object."""
- super(MultiHeadedAttentionSANMDecoder, self).__init__()
-
- self.dropout = nn.Dropout(p=dropout_rate)
-
- self.fsmn_block = nn.Conv1d(n_feat, n_feat,
- kernel_size, stride=1, padding=0, groups=n_feat, bias=False)
- # padding
- # padding
- left_padding = (kernel_size - 1) // 2
- if sanm_shfit > 0:
- left_padding = left_padding + sanm_shfit
- right_padding = kernel_size - 1 - left_padding
- self.pad_fn = nn.ConstantPad1d((left_padding, right_padding), 0.0)
- self.kernel_size = kernel_size
-
- def forward(self, inputs, mask, cache=None, mask_shfit_chunk=None):
- '''
- :param x: (#batch, time1, size).
- :param mask: Mask tensor (#batch, 1, time)
- :return:
- '''
- # print("in fsmn, inputs", inputs.size())
- b, t, d = inputs.size()
- # logging.info(
- # "mask: {}".format(mask.size()))
- if mask is not None:
- mask = torch.reshape(mask, (b ,-1, 1))
- # logging.info("in fsmn, mask: {}, {}".format(mask.size(), mask[0:100:50, :, :]))
- if mask_shfit_chunk is not None:
- # logging.info("in fsmn, mask_fsmn: {}, {}".format(mask_shfit_chunk.size(), mask_shfit_chunk[0:100:50, :, :]))
- mask = mask * mask_shfit_chunk
- # logging.info("in fsmn, mask_after_fsmn: {}, {}".format(mask.size(), mask[0:100:50, :, :]))
- # print("in fsmn, mask", mask.size())
- # print("in fsmn, inputs", inputs.size())
- inputs = inputs * mask
-
- x = inputs.transpose(1, 2)
- b, d, t = x.size()
- if cache is None:
- # print("in fsmn, cache is None, x", x.size())
-
- x = self.pad_fn(x)
- if not self.training:
- cache = x
- else:
- # print("in fsmn, cache is not None, x", x.size())
- # x = torch.cat((x, cache), dim=2)[:, :, :-1]
- # if t < self.kernel_size:
- # x = self.pad_fn(x)
- x = torch.cat((cache[:, :, 1:], x), dim=2)
- x = x[:, :, -(self.kernel_size+t-1):]
- # print("in fsmn, cache is not None, x_cat", x.size())
- cache = x
- x = self.fsmn_block(x)
- x = x.transpose(1, 2)
- # print("in fsmn, fsmn_out", x.size())
- if x.size(1) != inputs.size(1):
- inputs = inputs[:, -1, :]
-
- x = x + inputs
- x = self.dropout(x)
- if mask is not None:
- x = x * mask
- return x, cache
-
-class MultiHeadedAttentionCrossAtt(nn.Module):
- """Multi-Head Attention layer.
-
- Args:
- n_head (int): The number of heads.
- n_feat (int): The number of features.
- dropout_rate (float): Dropout rate.
-
- """
-
- def __init__(self, n_head, n_feat, dropout_rate, lora_list=None, lora_rank=8, lora_alpha=16, lora_dropout=0.1, encoder_output_size=None):
- """Construct an MultiHeadedAttention object."""
- super(MultiHeadedAttentionCrossAtt, self).__init__()
- assert n_feat % n_head == 0
- # We assume d_v always equals d_k
- self.d_k = n_feat // n_head
- self.h = n_head
- if lora_list is not None:
- if "q" in lora_list:
- self.linear_q = lora.Linear(n_feat, n_feat, r=lora_rank, lora_alpha=lora_alpha, lora_dropout=lora_dropout)
- else:
- self.linear_q = nn.Linear(n_feat, n_feat)
- lora_kv_list = ["k" in lora_list, "v" in lora_list]
- if lora_kv_list == [False, False]:
- self.linear_k_v = nn.Linear(n_feat if encoder_output_size is None else encoder_output_size, n_feat*2)
- else:
- self.linear_k_v = lora.MergedLinear(n_feat if encoder_output_size is None else encoder_output_size, n_feat * 2,
- r=lora_rank, lora_alpha=lora_alpha, lora_dropout=lora_dropout, enable_lora=lora_kv_list)
- if "o" in lora_list:
- self.linear_out = lora.Linear(n_feat, n_feat, r=lora_rank, lora_alpha=lora_alpha, lora_dropout=lora_dropout)
- else:
- self.linear_out = nn.Linear(n_feat, n_feat)
- else:
- self.linear_q = nn.Linear(n_feat, n_feat)
- self.linear_k_v = nn.Linear(n_feat if encoder_output_size is None else encoder_output_size, n_feat*2)
- self.linear_out = nn.Linear(n_feat, n_feat)
- self.attn = None
- self.dropout = nn.Dropout(p=dropout_rate)
-
- def forward_qkv(self, x, memory):
- """Transform query, key and value.
-
- Args:
- query (torch.Tensor): Query tensor (#batch, time1, size).
- key (torch.Tensor): Key tensor (#batch, time2, size).
- value (torch.Tensor): Value tensor (#batch, time2, size).
-
- Returns:
- torch.Tensor: Transformed query tensor (#batch, n_head, time1, d_k).
- torch.Tensor: Transformed key tensor (#batch, n_head, time2, d_k).
- torch.Tensor: Transformed value tensor (#batch, n_head, time2, d_k).
-
- """
-
- # print("in forward_qkv, x", x.size())
- b = x.size(0)
- q = self.linear_q(x)
- q_h = torch.reshape(q, (b, -1, self.h, self.d_k)).transpose(1, 2) # (batch, head, time1, d_k)
-
- k_v = self.linear_k_v(memory)
- k, v = torch.split(k_v, int(self.h*self.d_k), dim=-1)
- k_h = torch.reshape(k, (b, -1, self.h, self.d_k)).transpose(1, 2) # (batch, head, time2, d_k)
- v_h = torch.reshape(v, (b, -1, self.h, self.d_k)).transpose(1, 2) # (batch, head, time2, d_k)
-
-
- return q_h, k_h, v_h
-
- def forward_attention(self, value, scores, mask):
- """Compute attention context vector.
-
- Args:
- value (torch.Tensor): Transformed value (#batch, n_head, time2, d_k).
- scores (torch.Tensor): Attention score (#batch, n_head, time1, time2).
- mask (torch.Tensor): Mask (#batch, 1, time2) or (#batch, time1, time2).
-
- Returns:
- torch.Tensor: Transformed value (#batch, time1, d_model)
- weighted by the attention score (#batch, time1, time2).
-
- """
- n_batch = value.size(0)
- if mask is not None:
- mask = mask.unsqueeze(1).eq(0) # (batch, 1, *, time2)
- min_value = float(
- numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min
- )
- # logging.info(
- # "scores: {}, mask_size: {}".format(scores.size(), mask.size()))
- scores = scores.masked_fill(mask, min_value)
- self.attn = torch.softmax(scores, dim=-1).masked_fill(
- mask, 0.0
- ) # (batch, head, time1, time2)
- else:
- self.attn = torch.softmax(scores, dim=-1) # (batch, head, time1, time2)
-
- p_attn = self.dropout(self.attn)
- x = torch.matmul(p_attn, value) # (batch, head, time1, d_k)
- x = (
- x.transpose(1, 2).contiguous().view(n_batch, -1, self.h * self.d_k)
- ) # (batch, time1, d_model)
-
- return self.linear_out(x) # (batch, time1, d_model)
-
- def forward(self, x, memory, memory_mask):
- """Compute scaled dot product attention.
-
- Args:
- query (torch.Tensor): Query tensor (#batch, time1, size).
- key (torch.Tensor): Key tensor (#batch, time2, size).
- value (torch.Tensor): Value tensor (#batch, time2, size).
- mask (torch.Tensor): Mask tensor (#batch, 1, time2) or
- (#batch, time1, time2).
-
- Returns:
- torch.Tensor: Output tensor (#batch, time1, d_model).
-
- """
- q_h, k_h, v_h = self.forward_qkv(x, memory)
- q_h = q_h * self.d_k ** (-0.5)
- scores = torch.matmul(q_h, k_h.transpose(-2, -1))
- return self.forward_attention(v_h, scores, memory_mask)
-
- def forward_chunk(self, x, memory, cache=None, chunk_size=None, look_back=0):
- """Compute scaled dot product attention.
-
- Args:
- query (torch.Tensor): Query tensor (#batch, time1, size).
- key (torch.Tensor): Key tensor (#batch, time2, size).
- value (torch.Tensor): Value tensor (#batch, time2, size).
- mask (torch.Tensor): Mask tensor (#batch, 1, time2) or
- (#batch, time1, time2).
-
- Returns:
- torch.Tensor: Output tensor (#batch, time1, d_model).
-
- """
- q_h, k_h, v_h = self.forward_qkv(x, memory)
- if chunk_size is not None and look_back > 0:
- if cache is not None:
- k_h = torch.cat((cache["k"], k_h), dim=2)
- v_h = torch.cat((cache["v"], v_h), dim=2)
- cache["k"] = k_h[:, :, -(look_back * chunk_size[1]):, :]
- cache["v"] = v_h[:, :, -(look_back * chunk_size[1]):, :]
- else:
- cache_tmp = {"k": k_h[:, :, -(look_back * chunk_size[1]):, :],
- "v": v_h[:, :, -(look_back * chunk_size[1]):, :]}
- cache = cache_tmp
- q_h = q_h * self.d_k ** (-0.5)
- scores = torch.matmul(q_h, k_h.transpose(-2, -1))
- return self.forward_attention(v_h, scores, None), cache
-
-
-class MultiHeadSelfAttention(nn.Module):
- """Multi-Head Attention layer.
-
- Args:
- n_head (int): The number of heads.
- n_feat (int): The number of features.
- dropout_rate (float): Dropout rate.
-
- """
-
- def __init__(self, n_head, in_feat, n_feat, dropout_rate):
- """Construct an MultiHeadedAttention object."""
- super(MultiHeadSelfAttention, self).__init__()
- assert n_feat % n_head == 0
- # We assume d_v always equals d_k
- self.d_k = n_feat // n_head
- self.h = n_head
- self.linear_out = nn.Linear(n_feat, n_feat)
- self.linear_q_k_v = nn.Linear(in_feat, n_feat * 3)
- self.attn = None
- self.dropout = nn.Dropout(p=dropout_rate)
-
- def forward_qkv(self, x):
- """Transform query, key and value.
-
- Args:
- query (torch.Tensor): Query tensor (#batch, time1, size).
- key (torch.Tensor): Key tensor (#batch, time2, size).
- value (torch.Tensor): Value tensor (#batch, time2, size).
-
- Returns:
- torch.Tensor: Transformed query tensor (#batch, n_head, time1, d_k).
- torch.Tensor: Transformed key tensor (#batch, n_head, time2, d_k).
- torch.Tensor: Transformed value tensor (#batch, n_head, time2, d_k).
-
- """
- b, t, d = x.size()
- q_k_v = self.linear_q_k_v(x)
- q, k, v = torch.split(q_k_v, int(self.h * self.d_k), dim=-1)
- q_h = torch.reshape(q, (b, t, self.h, self.d_k)).transpose(1, 2) # (batch, head, time1, d_k)
- k_h = torch.reshape(k, (b, t, self.h, self.d_k)).transpose(1, 2) # (batch, head, time2, d_k)
- v_h = torch.reshape(v, (b, t, self.h, self.d_k)).transpose(1, 2) # (batch, head, time2, d_k)
-
- return q_h, k_h, v_h, v
-
- def forward_attention(self, value, scores, mask, mask_att_chunk_encoder=None):
- """Compute attention context vector.
-
- Args:
- value (torch.Tensor): Transformed value (#batch, n_head, time2, d_k).
- scores (torch.Tensor): Attention score (#batch, n_head, time1, time2).
- mask (torch.Tensor): Mask (#batch, 1, time2) or (#batch, time1, time2).
-
- Returns:
- torch.Tensor: Transformed value (#batch, time1, d_model)
- weighted by the attention score (#batch, time1, time2).
-
- """
- n_batch = value.size(0)
- if mask is not None:
- if mask_att_chunk_encoder is not None:
- mask = mask * mask_att_chunk_encoder
-
- mask = mask.unsqueeze(1).eq(0) # (batch, 1, *, time2)
-
- min_value = float(
- numpy.finfo(torch.tensor(0, dtype=scores.dtype).numpy().dtype).min
- )
- scores = scores.masked_fill(mask, min_value)
- self.attn = torch.softmax(scores, dim=-1).masked_fill(
- mask, 0.0
- ) # (batch, head, time1, time2)
- else:
- self.attn = torch.softmax(scores, dim=-1) # (batch, head, time1, time2)
-
- p_attn = self.dropout(self.attn)
- x = torch.matmul(p_attn, value) # (batch, head, time1, d_k)
- x = (
- x.transpose(1, 2).contiguous().view(n_batch, -1, self.h * self.d_k)
- ) # (batch, time1, d_model)
-
- return self.linear_out(x) # (batch, time1, d_model)
-
- def forward(self, x, mask, mask_att_chunk_encoder=None):
- """Compute scaled dot product attention.
-
- Args:
- query (torch.Tensor): Query tensor (#batch, time1, size).
- key (torch.Tensor): Key tensor (#batch, time2, size).
- value (torch.Tensor): Value tensor (#batch, time2, size).
- mask (torch.Tensor): Mask tensor (#batch, 1, time2) or
- (#batch, time1, time2).
-
- Returns:
- torch.Tensor: Output tensor (#batch, time1, d_model).
-
- """
- q_h, k_h, v_h, v = self.forward_qkv(x)
- q_h = q_h * self.d_k ** (-0.5)
- scores = torch.matmul(q_h, k_h.transpose(-2, -1))
- att_outs = self.forward_attention(v_h, scores, mask, mask_att_chunk_encoder)
- return att_outs
class RelPositionMultiHeadedAttentionChunk(torch.nn.Module):
"""RelPositionMultiHeadedAttention definition.
@@ -978,21 +548,9 @@
"""
n_batch = query.size(0)
- q = (
- self.linear_q(query)
- .view(n_batch, -1, self.num_heads, self.d_k)
- .transpose(1, 2)
- )
- k = (
- self.linear_k(key)
- .view(n_batch, -1, self.num_heads, self.d_k)
- .transpose(1, 2)
- )
- v = (
- self.linear_v(value)
- .view(n_batch, -1, self.num_heads, self.d_k)
- .transpose(1, 2)
- )
+ q = self.linear_q(query).view(n_batch, -1, self.num_heads, self.d_k).transpose(1, 2)
+ k = self.linear_k(key).view(n_batch, -1, self.num_heads, self.d_k).transpose(1, 2)
+ v = self.linear_v(value).view(n_batch, -1, self.num_heads, self.d_k).transpose(1, 2)
return q, k, v
@@ -1023,9 +581,7 @@
attn_output = torch.matmul(attn_output, value)
attn_output = self.linear_out(
- attn_output.transpose(1, 2)
- .contiguous()
- .view(batch_size, -1, self.num_heads * self.d_k)
+ attn_output.transpose(1, 2).contiguous().view(batch_size, -1, self.num_heads * self.d_k)
)
return attn_output
@@ -1055,37 +611,3 @@
q, k, v = self.forward_qkv(query, key, value)
scores = self.compute_att_score(q, k, pos_enc, left_context=left_context)
return self.forward_attention(v, scores, mask, chunk_mask=chunk_mask)
-
-
-class CosineDistanceAttention(nn.Module):
- """ Compute Cosine Distance between spk decoder output and speaker profile
- Args:
- profile_path: speaker profile file path (.npy file)
- """
-
- def __init__(self):
- super().__init__()
- self.softmax = nn.Softmax(dim=-1)
-
- def forward(self, spk_decoder_out, profile, profile_lens=None):
- """
- Args:
- spk_decoder_out(torch.Tensor):(B, L, D)
- spk_profiles(torch.Tensor):(B, N, D)
- """
- x = spk_decoder_out.unsqueeze(2) # (B, L, 1, D)
- if profile_lens is not None:
-
- mask = (make_pad_mask(profile_lens)[:, None, :]).to(profile.device)
- min_value = float(
- numpy.finfo(torch.tensor(0, dtype=x.dtype).numpy().dtype).min
- )
- weights_not_softmax=F.cosine_similarity(x, profile.unsqueeze(1), dim=-1).masked_fill(mask, min_value)
- weights = self.softmax(weights_not_softmax).masked_fill(mask, 0.0) # (B, L, N)
- else:
- x = x[:, -1:, :, :]
- weights_not_softmax=F.cosine_similarity(x, profile.unsqueeze(1).to(x.device), dim=-1)
- weights = self.softmax(weights_not_softmax) # (B, 1, N)
- spk_embedding = torch.matmul(weights, profile.to(weights.device)) # (B, L, D)
-
- return spk_embedding, weights
--
Gitblit v1.9.1