resnet 50

注意点提示：一个板块进行了三次卷积，is_1x1conv=False 是捷径是否需要调整维度，利用for循环多次重复使用模块，有的3*3的卷积核步长为2将特征图大小变为一半，Layers = [3, 4, 6, 3]。filter1, filter2, filter3 = filters。
def ResNet50(num_classes=10):
return ResNet(Bottleneck, [3,4,6,3], num_classes)

class Bottleneck(nn.Module):
expansion = 4

def __init__(self, in_planes, planes, stride=1):
    super(Bottleneck, self).__init__()
    self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, bias=False)
    self.bn1 = nn.BatchNorm2d(planes)
    self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
    self.bn2 = nn.BatchNorm2d(planes)
    self.conv3 = nn.Conv2d(planes, self.expansion * planes, kernel_size=1, bias=False)
    self.bn3 = nn.BatchNorm2d(self.expansion * 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, bias=False),
            nn.BatchNorm2d(self.expansion * planes)
        )

def forward(self, x):
            out = F.relu(self.bn1(self.conv1(x)))
            out = F.relu(self.bn2(self.conv2(out)))
            out = self.bn3(self.conv3(out))
            out += self.shortcut(x)
            out = F.relu(out)
            return out

class ResNet(nn.Module):
def init(self, block, num_blocks, num_classes=10): # Bottleneck, [3,4,6,3], num_classes=10
super(ResNet, self).init()
self.in_planes = 64

    self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
    self.bn1 = nn.BatchNorm2d(64)
    self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)  # Bottleneck, planes=64, 3, stride=1
    self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)  # Bottleneck, planes=128, 4, stride=2
    self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)  # Bottleneck, planes=256, 6, stride=2
    self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)  # Bottleneck, planes=512, 3, stride=2
    self.linear = nn.Linear(512 * block.expansion, num_classes)

def _make_layer(self, block, planes, num_blocks, stride): 
    strides = [stride] + [1] * (num_blocks - 1)  
    layers = []
    for stride in strides:
        layers.append(block(self.in_planes, planes, stride))
        self.in_planes = planes * block.expansion
    return nn.Sequential(*layers)

def forward(self, x, out_feature=False):
    out = F.relu(self.bn1(self.conv1(x)))
    out = self.layer1(out)
    out = self.layer2(out)
    out = self.layer3(out)
    out = self.layer4(out)
    out = F.avg_pool2d(out, 4)
    feature = out.view(out.size(0), -1)
    out = self.linear(feature)
    if out_feature == False:
        return out
    else:
        return out, feature