From f2d8ded57f6403696001d39dd07a1396e5a03658 Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 11 三月 2024 01:24:43 +0800
Subject: [PATCH] export onnx (#1455)
---
funasr/models/sanm/attention.py | 68 +++++++++++++++++++++++++++++++--
1 files changed, 63 insertions(+), 5 deletions(-)
diff --git a/funasr/models/sanm/attention.py b/funasr/models/sanm/attention.py
index f48617c..09a1f07 100644
--- a/funasr/models/sanm/attention.py
+++ b/funasr/models/sanm/attention.py
@@ -303,6 +303,64 @@
att_outs = self.forward_attention(v_h, scores, None)
return att_outs + fsmn_memory, cache
+class MultiHeadedAttentionSANMExport(nn.Module):
+ def __init__(self, model):
+ super().__init__()
+ self.d_k = model.d_k
+ self.h = model.h
+ self.linear_out = model.linear_out
+ self.linear_q_k_v = model.linear_q_k_v
+ self.fsmn_block = model.fsmn_block
+ self.pad_fn = model.pad_fn
+
+ self.attn = None
+ self.all_head_size = self.h * self.d_k
+
+ def forward(self, x, mask):
+ mask_3d_btd, mask_4d_bhlt = mask
+ q_h, k_h, v_h, v = self.forward_qkv(x)
+ fsmn_memory = self.forward_fsmn(v, mask_3d_btd)
+ 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_4d_bhlt)
+ return att_outs + fsmn_memory
+
+ 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, x):
+ 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 = self.transpose_for_scores(q)
+ k_h = self.transpose_for_scores(k)
+ v_h = self.transpose_for_scores(v)
+ return q_h, k_h, v_h, v
+
+ def forward_fsmn(self, inputs, mask):
+ # b, t, d = inputs.size()
+ # mask = torch.reshape(mask, (b, -1, 1))
+ inputs = inputs * mask
+ x = inputs.transpose(1, 2)
+ x = self.pad_fn(x)
+ x = self.fsmn_block(x)
+ x = x.transpose(1, 2)
+ x = x + inputs
+ x = x * mask
+ 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 MultiHeadedAttentionSANMDecoder(nn.Module):
@@ -449,7 +507,7 @@
return q_h, k_h, v_h
- def forward_attention(self, value, scores, mask):
+ def forward_attention(self, value, scores, mask, ret_attn=False):
"""Compute attention context vector.
Args:
@@ -476,16 +534,16 @@
) # (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)
-
+ if ret_attn:
+ return self.linear_out(x), self.attn # (batch, time1, d_model)
return self.linear_out(x) # (batch, time1, d_model)
- def forward(self, x, memory, memory_mask):
+ def forward(self, x, memory, memory_mask, ret_attn=False):
"""Compute scaled dot product attention.
Args:
@@ -502,7 +560,7 @@
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)
+ return self.forward_attention(v_h, scores, memory_mask, ret_attn=ret_attn)
def forward_chunk(self, x, memory, cache=None, chunk_size=None, look_back=0):
"""Compute scaled dot product attention.
--
Gitblit v1.9.1