From 1d4ab65c8bfebaecbcb0eec0064bae9a321cad75 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 14 二月 2023 16:27:37 +0800
Subject: [PATCH] export model

---
 funasr/modules/subsampling.py |  129 +++++++++++++++++++++++++++++++++++++++----
 1 files changed, 117 insertions(+), 12 deletions(-)

diff --git a/funasr/modules/subsampling.py b/funasr/modules/subsampling.py
index f9a1c16..d492ccf 100644
--- a/funasr/modules/subsampling.py
+++ b/funasr/modules/subsampling.py
@@ -5,12 +5,12 @@
 #  Apache 2.0  (http://www.apache.org/licenses/LICENSE-2.0)
 
 """Subsampling layer definition."""
-
+import numpy as np
 import torch
 import torch.nn.functional as F
 from funasr.modules.embedding import PositionalEncoding
-
-
+import logging
+from funasr.modules.streaming_utils.utils import sequence_mask
 class TooShortUttError(Exception):
     """Raised when the utt is too short for subsampling.
 
@@ -87,6 +87,72 @@
         if x_mask is None:
             return x, None
         return x, x_mask[:, :, :-2:2][:, :, :-2:2]
+
+    def __getitem__(self, key):
+        """Get item.
+
+        When reset_parameters() is called, if use_scaled_pos_enc is used,
+            return the positioning encoding.
+
+        """
+        if key != -1:
+            raise NotImplementedError("Support only `-1` (for `reset_parameters`).")
+        return self.out[key]
+
+class Conv2dSubsamplingPad(torch.nn.Module):
+    """Convolutional 2D subsampling (to 1/4 length).
+
+    Args:
+        idim (int): Input dimension.
+        odim (int): Output dimension.
+        dropout_rate (float): Dropout rate.
+        pos_enc (torch.nn.Module): Custom position encoding layer.
+
+    """
+
+    def __init__(self, idim, odim, dropout_rate, pos_enc=None):
+        """Construct an Conv2dSubsampling object."""
+        super(Conv2dSubsamplingPad, self).__init__()
+        self.conv = torch.nn.Sequential(
+            torch.nn.Conv2d(1, odim, 3, 2, padding=(0, 0)),
+            torch.nn.ReLU(),
+            torch.nn.Conv2d(odim, odim, 3, 2, padding=(0, 0)),
+            torch.nn.ReLU(),
+        )
+        self.out = torch.nn.Sequential(
+            torch.nn.Linear(odim * (((idim - 1) // 2 - 1) // 2), odim),
+            pos_enc if pos_enc is not None else PositionalEncoding(odim, dropout_rate),
+        )
+        self.pad_fn = torch.nn.ConstantPad1d((0, 4), 0.0)
+
+    def forward(self, x, x_mask):
+        """Subsample x.
+
+        Args:
+            x (torch.Tensor): Input tensor (#batch, time, idim).
+            x_mask (torch.Tensor): Input mask (#batch, 1, time).
+
+        Returns:
+            torch.Tensor: Subsampled tensor (#batch, time', odim),
+                where time' = time // 4.
+            torch.Tensor: Subsampled mask (#batch, 1, time'),
+                where time' = time // 4.
+
+        """
+        x = x.transpose(1, 2)
+        x = self.pad_fn(x)
+        x = x.transpose(1, 2)
+        x = x.unsqueeze(1)  # (b, c, t, f)
+        x = self.conv(x)
+        b, c, t, f = x.size()
+        x = self.out(x.transpose(1, 2).contiguous().view(b, t, c * f))
+        if x_mask is None:
+            return x, None
+        x_len = torch.sum(x_mask[:, 0, :], dim=-1)
+        x_len = (x_len - 1) // 2 + 1
+        x_len = (x_len - 1) // 2 + 1
+        mask = sequence_mask(x_len, None, x_len.dtype, x[0].device)
+        return x, mask[:, None, :]
 
     def __getitem__(self, key):
         """Get item.
@@ -267,12 +333,17 @@
 
     """
 
-    def __init__(self, idim, odim, kernel_size, stride, pad):
+    def __init__(self, idim, odim, kernel_size, stride, pad,
+                 tf2torch_tensor_name_prefix_torch: str = "stride_conv",
+                 tf2torch_tensor_name_prefix_tf: str = "seq2seq/proj_encoder/downsampling",
+                 ):
         super(Conv1dSubsampling, self).__init__()
         self.conv = torch.nn.Conv1d(idim, odim, kernel_size, stride)
         self.pad_fn = torch.nn.ConstantPad1d(pad, 0.0)
         self.stride = stride
         self.odim = odim
+        self.tf2torch_tensor_name_prefix_torch = tf2torch_tensor_name_prefix_torch
+        self.tf2torch_tensor_name_prefix_tf = tf2torch_tensor_name_prefix_tf
 
     def output_size(self) -> int:
         return self.odim
@@ -292,13 +363,47 @@
         x_len = (x_len - 1) // self.stride + 1
         return x, x_len
 
-    def __getitem__(self, key):
-        """Get item.
+    def gen_tf2torch_map_dict(self):
+        tensor_name_prefix_torch = self.tf2torch_tensor_name_prefix_torch
+        tensor_name_prefix_tf = self.tf2torch_tensor_name_prefix_tf
+        map_dict_local = {
+            ## predictor
+            "{}.conv.weight".format(tensor_name_prefix_torch):
+                {"name": "{}/conv1d/kernel".format(tensor_name_prefix_tf),
+                 "squeeze": None,
+                 "transpose": (2, 1, 0),
+                 },  # (256,256,3),(3,256,256)
+            "{}.conv.bias".format(tensor_name_prefix_torch):
+                {"name": "{}/conv1d/bias".format(tensor_name_prefix_tf),
+                 "squeeze": None,
+                 "transpose": None,
+                 },  # (256,),(256,)
+        }
+        return map_dict_local
 
-        When reset_parameters() is called, if use_scaled_pos_enc is used,
-            return the positioning encoding.
+    def convert_tf2torch(self,
+                         var_dict_tf,
+                         var_dict_torch,
+                         ):
+    
+        map_dict = self.gen_tf2torch_map_dict()
+    
+        var_dict_torch_update = dict()
+        for name in sorted(var_dict_torch.keys(), reverse=False):
+            names = name.split('.')
+            if names[0] == self.tf2torch_tensor_name_prefix_torch:
+                name_tf = map_dict[name]["name"]
+                data_tf = var_dict_tf[name_tf]
+                if map_dict[name]["squeeze"] is not None:
+                    data_tf = np.squeeze(data_tf, axis=map_dict[name]["squeeze"])
+                if map_dict[name]["transpose"] is not None:
+                    data_tf = np.transpose(data_tf, map_dict[name]["transpose"])
+                data_tf = torch.from_numpy(data_tf).type(torch.float32).to("cpu")
+            
+                var_dict_torch_update[name] = data_tf
+            
+                logging.info(
+                    "torch tensor: {}, {}, loading from tf tensor: {}, {}".format(name, data_tf.size(), name_tf,
+                                                                                  var_dict_tf[name_tf].shape))
+        return var_dict_torch_update
 
-        """
-        if key != -1:
-            raise NotImplementedError("Support only `-1` (for `reset_parameters`).")
-        return self.out[key]

--
Gitblit v1.9.1