def __init__(self, inplanes, planes, stride=1, downsample=None): super(BasicBlock, self).__init__() self.conv1 = conv3x3(inplanes, planes, stride) self.bn1 = TransNorm2d(planes) ## replace self.relu = nn.ReLU(inplace=True) self.conv2 = conv3x3(planes, planes) self.bn2 = TransNorm2d(planes) ## replace self.downsample = downsample self.stride = stride
def _make_layer(self, block, planes, blocks, stride=1, type=None): downsample = None if stride != 1 or self.inplanes != planes * block.expansion: if type == 'normal': downsample = nn.Sequential( nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(planes * block.expansion)) else: #print('---here') downsample = nn.Sequential( nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False), TransNorm2d(planes * block.expansion)) layers = [] layers.append(block(self.inplanes, planes, stride, downsample, type)) # type 추가하기 self.inplanes = planes * block.expansion for i in range(1, blocks): layers.append(block(self.inplanes, planes, type=type)) return nn.Sequential(*layers)
def __init__(self, inplanes, planes, stride=1, downsample=None): super(Bottleneck, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) self.bn1 = TransNorm2d(planes) ## replace self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) self.bn2 = TransNorm2d(planes) ## replace self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False) self.bn3 = TransNorm2d(planes * 4) ## replace self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride
def __init__(self, block, layers, num_classes=1000): self.inplanes = 64 super(ResNet, self).__init__() self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False) self.bn1 = TransNorm2d(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) self.layer3 = self._make_layer(block, 256, layers[2], stride=2) self.layer4 = self._make_layer(block, 512, layers[3], stride=2) self.avgpool = nn.AvgPool2d(7, stride=1) self.fc = nn.Linear(512 * block.expansion, num_classes) 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)) elif isinstance(m, nn.BatchNorm2d): m.weight.data.fill_(1) m.bias.data.zero_()
def __init__(self, inplanes, planes, stride=1, downsample=None, type=None): # type이 어떻게 넘어가는지 확인 용 super(Bottleneck, self).__init__() self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False) if type == 'normal': self.bn1 = nn.BatchNorm2d(planes) else: self.bn1 = TransNorm2d(planes) self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False) if type == 'normal': self.bn2 = nn.BatchNorm2d(planes) else: self.bn2 = TransNorm2d(planes) self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False) if type == 'normal': self.bn3 = nn.BatchNorm2d(planes * 4) else: self.bn3 = TransNorm2d(planes * 4) self.relu = nn.ReLU(inplace=True) self.downsample = downsample self.stride = stride
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), TransNorm2d(planes * block.expansion), ) layers = [] layers.append(block(self.inplanes, planes, stride, downsample)) self.inplanes = planes * block.expansion for i in range(1, blocks): layers.append(block(self.inplanes, planes)) return nn.Sequential(*layers)