ResNet-Model(pytorch版本)

$$ResNet-Model(pytorch版本)$$

import torch
import torch.nn as nn
import torch.nn.functional as F

# 用于ResNet18和34的残差块，用的是2个3x3的卷积
class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, in_planes, planes, stride=1):
        super(BasicBlock, self).__init__()
        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3,
                               stride=stride, 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()
        # 经过处理后的x要与x的维度相同(尺寸和深度)
        # 如果不相同，需要添加卷积+BN来变换为同一维度
        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 = self.bn2(self.conv2(out))
        out += self.shortcut(x)
        out = F.relu(out)
        return out


# 用于ResNet50,101和152的残差块，用的是1x1+3x3+1x1的卷积
class Bottleneck(nn.Module):
    # 前面1x1和3x3卷积的filter个数相等，最后1x1卷积是其expansion倍
    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=5,num_linear=25088):
        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)
        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
        self.linear = nn.Linear(num_linear, 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 = 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)
        out = out.view(out.size(0), -1)
        out = self.linear(out)
        return out


def ResNet18(num_classes,num_linear):
    return ResNet(BasicBlock, [2, 2, 2, 2],num_classes,num_linear)


def ResNet34(num_classes,num_linear):
    return ResNet(BasicBlock, [3, 4, 6, 3],num_classes,num_linear)


def ResNet50(num_classes,num_linear):
    return ResNet(Bottleneck, [3, 4, 6, 3],num_classes,num_linear)


def ResNet101(num_classes,num_linear):
    return ResNet(Bottleneck, [3, 4, 23, 3],num_classes,num_linear)


def ResNet152(num_classes,num_linear):
    return ResNet(Bottleneck, [3, 8, 36, 3],num_classes,num_linear)

# 随机生成输入数据
rgb = torch.randn(1, 3, 224, 224)
# 定义网络
# num_linear的设置是为了，随着输入图片数据大小的改变，使线性层的神经元数量可以匹配成功
# 默认输入图片数据大小为224*224
net = ResNet18(num_classes=8,num_linear=25088)
# 前向传播
out = net(rgb)
print('-----'*5)
# 打印输出大小
print(out.shape)
print('-----'*5)

# 随机生成输入数据
rgb = torch.randn(1, 3, 224, 224)
# 定义网络
# num_linear的设置是为了，随着输入图片数据大小的改变，使线性层的神经元数量可以匹配成功
# 默认输入图片数据大小为224*224
net = ResNet34(num_classes=8,num_linear=25088)
# 前向传播
out = net(rgb)
print('-----'*5)
# 打印输出大小
print(out.shape)
print('-----'*5)