|
import torch |
|
import torch.nn as nn |
|
import math |
|
|
|
'''https://github.com/blandocs/Tag2Pix/blob/master/model/pretrained.py''' |
|
|
|
|
|
class Selayer(nn.Module): |
|
def __init__(self, inplanes): |
|
super(Selayer, self).__init__() |
|
self.global_avgpool = nn.AdaptiveAvgPool2d(1) |
|
self.conv1 = nn.Conv2d(inplanes, inplanes // 16, kernel_size=1, stride=1) |
|
self.conv2 = nn.Conv2d(inplanes // 16, inplanes, kernel_size=1, stride=1) |
|
self.relu = nn.ReLU(inplace=True) |
|
self.sigmoid = nn.Sigmoid() |
|
|
|
def forward(self, x): |
|
out = self.global_avgpool(x) |
|
out = self.conv1(out) |
|
out = self.relu(out) |
|
out = self.conv2(out) |
|
out = self.sigmoid(out) |
|
|
|
return x * out |
|
|
|
|
|
class BottleneckX_Origin(nn.Module): |
|
expansion = 4 |
|
|
|
def __init__(self, inplanes, planes, cardinality, stride=1, downsample=None): |
|
super(BottleneckX_Origin, self).__init__() |
|
self.conv1 = nn.Conv2d(inplanes, planes * 2, kernel_size=1, bias=False) |
|
self.bn1 = nn.BatchNorm2d(planes * 2) |
|
|
|
self.conv2 = nn.Conv2d(planes * 2, planes * 2, kernel_size=3, stride=stride, |
|
padding=1, groups=cardinality, bias=False) |
|
self.bn2 = nn.BatchNorm2d(planes * 2) |
|
|
|
self.conv3 = nn.Conv2d(planes * 2, planes * 4, kernel_size=1, bias=False) |
|
self.bn3 = nn.BatchNorm2d(planes * 4) |
|
|
|
self.selayer = Selayer(planes * 4) |
|
|
|
self.relu = nn.ReLU(inplace=True) |
|
self.downsample = downsample |
|
self.stride = stride |
|
|
|
def forward(self, x): |
|
residual = x |
|
|
|
out = self.conv1(x) |
|
out = self.bn1(out) |
|
out = self.relu(out) |
|
|
|
out = self.conv2(out) |
|
out = self.bn2(out) |
|
out = self.relu(out) |
|
|
|
out = self.conv3(out) |
|
out = self.bn3(out) |
|
|
|
out = self.selayer(out) |
|
|
|
if self.downsample is not None: |
|
residual = self.downsample(x) |
|
|
|
out += residual |
|
out = self.relu(out) |
|
|
|
return out |
|
|
|
class SEResNeXt_extractor(nn.Module): |
|
def __init__(self, block, layers, input_channels=3, cardinality=32): |
|
super(SEResNeXt_extractor, self).__init__() |
|
self.cardinality = cardinality |
|
self.inplanes = 64 |
|
self.input_channels = input_channels |
|
|
|
self.conv1 = nn.Conv2d(input_channels, 64, kernel_size=7, stride=2, padding=3, |
|
bias=False) |
|
self.bn1 = nn.BatchNorm2d(64) |
|
self.relu = nn.ReLU(inplace=True) |
|
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1) |
|
|
|
self.layer1 = self._make_layer(block, 64, layers[0]) |
|
self.layer2 = self._make_layer(block, 128, layers[1], stride=2) |
|
|
|
for m in self.modules(): |
|
if isinstance(m, nn.Conv2d): |
|
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels |
|
m.weight.data.normal_(0, math.sqrt(2. / n)) |
|
if m.bias is not None: |
|
m.bias.data.zero_() |
|
elif isinstance(m, nn.BatchNorm2d): |
|
m.weight.data.fill_(1) |
|
m.bias.data.zero_() |
|
|
|
def _make_layer(self, block, planes, blocks, stride=1): |
|
downsample = None |
|
if stride != 1 or self.inplanes != planes * block.expansion: |
|
downsample = nn.Sequential( |
|
nn.Conv2d(self.inplanes, planes * block.expansion, |
|
kernel_size=1, stride=stride, bias=False), |
|
nn.BatchNorm2d(planes * block.expansion), |
|
) |
|
|
|
layers = [] |
|
layers.append(block(self.inplanes, planes, self.cardinality, stride, downsample)) |
|
self.inplanes = planes * block.expansion |
|
for i in range(1, blocks): |
|
layers.append(block(self.inplanes, planes, self.cardinality)) |
|
|
|
return nn.Sequential(*layers) |
|
|
|
def forward(self, x): |
|
x = self.conv1(x) |
|
x = self.bn1(x) |
|
x = self.relu(x) |
|
x = self.maxpool(x) |
|
|
|
x = self.layer1(x) |
|
x = self.layer2(x) |
|
|
|
return x |
|
|
|
def get_seresnext_extractor(): |
|
return SEResNeXt_extractor(BottleneckX_Origin, [3, 4, 6, 3], 1) |