File size: 9,351 Bytes
9a83644 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 |
# Copyright 3D-Speaker (https://github.com/alibaba-damo-academy/3D-Speaker). All Rights Reserved.
# Licensed under the Apache License, Version 2.0 (http://www.apache.org/licenses/LICENSE-2.0)
import torch
import torch.nn.functional as F
import torch.utils.checkpoint as cp
from torch import nn
def get_nonlinear(config_str, channels):
nonlinear = nn.Sequential()
for name in config_str.split('-'):
if name == 'relu':
nonlinear.add_module('relu', nn.ReLU(inplace=True))
elif name == 'prelu':
nonlinear.add_module('prelu', nn.PReLU(channels))
elif name == 'batchnorm':
nonlinear.add_module('batchnorm', nn.BatchNorm1d(channels))
elif name == 'batchnorm_':
nonlinear.add_module('batchnorm',
nn.BatchNorm1d(channels, affine=False))
else:
raise ValueError('Unexpected module ({}).'.format(name))
return nonlinear
def statistics_pooling(x, dim=-1, keepdim=False, unbiased=True, eps=1e-2):
mean = x.mean(dim=dim)
std = x.std(dim=dim, unbiased=unbiased)
stats = torch.cat([mean, std], dim=-1)
if keepdim:
stats = stats.unsqueeze(dim=dim)
return stats
class StatsPool(nn.Module):
def forward(self, x):
return statistics_pooling(x)
class TDNNLayer(nn.Module):
def __init__(self,
in_channels,
out_channels,
kernel_size,
stride=1,
padding=0,
dilation=1,
bias=False,
config_str='batchnorm-relu'):
super(TDNNLayer, self).__init__()
if padding < 0:
assert kernel_size % 2 == 1, 'Expect equal paddings, but got even kernel size ({})'.format(
kernel_size)
padding = (kernel_size - 1) // 2 * dilation
self.linear = nn.Conv1d(in_channels,
out_channels,
kernel_size,
stride=stride,
padding=padding,
dilation=dilation,
bias=bias)
self.nonlinear = get_nonlinear(config_str, out_channels)
def forward(self, x):
x = self.linear(x)
x = self.nonlinear(x)
return x
class CAMLayer(nn.Module):
def __init__(self,
bn_channels,
out_channels,
kernel_size,
stride,
padding,
dilation,
bias,
reduction=2):
super(CAMLayer, self).__init__()
self.linear_local = nn.Conv1d(bn_channels,
out_channels,
kernel_size,
stride=stride,
padding=padding,
dilation=dilation,
bias=bias)
self.linear1 = nn.Conv1d(bn_channels, bn_channels // reduction, 1)
self.relu = nn.ReLU(inplace=True)
self.linear2 = nn.Conv1d(bn_channels // reduction, out_channels, 1)
self.sigmoid = nn.Sigmoid()
def forward(self, x):
y = self.linear_local(x)
context = x.mean(-1, keepdim=True)+self.seg_pooling(x)
context = self.relu(self.linear1(context))
m = self.sigmoid(self.linear2(context))
return y*m
def seg_pooling(self, x, seg_len=100, stype='avg'):
if stype == 'avg':
seg = F.avg_pool1d(x, kernel_size=seg_len, stride=seg_len, ceil_mode=True)
elif stype == 'max':
seg = F.max_pool1d(x, kernel_size=seg_len, stride=seg_len, ceil_mode=True)
else:
raise ValueError('Wrong segment pooling type.')
shape = seg.shape
seg = seg.unsqueeze(-1).expand(*shape, seg_len).reshape(*shape[:-1], -1)
seg = seg[..., :x.shape[-1]]
return seg
class CAMDenseTDNNLayer(nn.Module):
def __init__(self,
in_channels,
out_channels,
bn_channels,
kernel_size,
stride=1,
dilation=1,
bias=False,
config_str='batchnorm-relu',
memory_efficient=False):
super(CAMDenseTDNNLayer, self).__init__()
assert kernel_size % 2 == 1, 'Expect equal paddings, but got even kernel size ({})'.format(
kernel_size)
padding = (kernel_size - 1) // 2 * dilation
self.memory_efficient = memory_efficient
self.nonlinear1 = get_nonlinear(config_str, in_channels)
self.linear1 = nn.Conv1d(in_channels, bn_channels, 1, bias=False)
self.nonlinear2 = get_nonlinear(config_str, bn_channels)
self.cam_layer = CAMLayer(bn_channels,
out_channels,
kernel_size,
stride=stride,
padding=padding,
dilation=dilation,
bias=bias)
def bn_function(self, x):
return self.linear1(self.nonlinear1(x))
def forward(self, x):
if self.training and self.memory_efficient:
x = cp.checkpoint(self.bn_function, x)
else:
x = self.bn_function(x)
x = self.cam_layer(self.nonlinear2(x))
return x
class CAMDenseTDNNBlock(nn.ModuleList):
def __init__(self,
num_layers,
in_channels,
out_channels,
bn_channels,
kernel_size,
stride=1,
dilation=1,
bias=False,
config_str='batchnorm-relu',
memory_efficient=False):
super(CAMDenseTDNNBlock, self).__init__()
for i in range(num_layers):
layer = CAMDenseTDNNLayer(in_channels=in_channels + i * out_channels,
out_channels=out_channels,
bn_channels=bn_channels,
kernel_size=kernel_size,
stride=stride,
dilation=dilation,
bias=bias,
config_str=config_str,
memory_efficient=memory_efficient)
self.add_module('tdnnd%d' % (i + 1), layer)
def forward(self, x):
for layer in self:
x = torch.cat([x, layer(x)], dim=1)
return x
class TransitLayer(nn.Module):
def __init__(self,
in_channels,
out_channels,
bias=True,
config_str='batchnorm-relu'):
super(TransitLayer, self).__init__()
self.nonlinear = get_nonlinear(config_str, in_channels)
self.linear = nn.Conv1d(in_channels, out_channels, 1, bias=bias)
def forward(self, x):
x = self.nonlinear(x)
x = self.linear(x)
return x
class DenseLayer(nn.Module):
def __init__(self,
in_channels,
out_channels,
bias=False,
config_str='batchnorm-relu'):
super(DenseLayer, self).__init__()
self.linear = nn.Conv1d(in_channels, out_channels, 1, bias=bias)
self.nonlinear = get_nonlinear(config_str, out_channels)
def forward(self, x):
if len(x.shape) == 2:
x = self.linear(x.unsqueeze(dim=-1)).squeeze(dim=-1)
else:
x = self.linear(x)
x = self.nonlinear(x)
return x
class BasicResBlock(nn.Module):
expansion = 1
def __init__(self, in_planes, planes, stride=1):
super(BasicResBlock, self).__init__()
self.conv1 = nn.Conv2d(in_planes,
planes,
kernel_size=3,
stride=(stride, 1),
padding=1,
bias=False)
self.bn1 = nn.BatchNorm2d(planes)
self.conv2 = nn.Conv2d(planes,
planes,
kernel_size=3,
stride=1,
padding=1,
bias=False)
self.bn2 = nn.BatchNorm2d(planes)
self.shortcut = nn.Sequential()
if stride != 1 or in_planes != self.expansion * planes:
self.shortcut = nn.Sequential(
nn.Conv2d(in_planes,
self.expansion * planes,
kernel_size=1,
stride=(stride, 1),
bias=False),
nn.BatchNorm2d(self.expansion * planes))
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
out += self.shortcut(x)
out = F.relu(out)
return out |