resnet_yolo.py

import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
import torch.nn.functional as F
import torch

__all__ = ['ResNet', 'resnet18', 'resnet34', 'resnet50', 'resnet101',
           'resnet152']

model_urls = {
    'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
    'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
    'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
    'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
    'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
}


def conv3x3(in_planes, out_planes, stride=1):
    return nn.Conv2d(in_channels=in_planes, out_channels=out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)
    # 参数分为别输入通道数、输出通道数、卷积核大小、滑动步长、padding大小、是否将学习到的bias加到输出中

class BasicBlock(nn.Module):
    # 结构：input --> conv1 --> BN --> ReLU --> conv2 --> BN --> + --> ReLU --> out
    #        |                                                  |
    #         --------------------residual----------------------
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        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)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    # 区别于BasicBlock这里有3个conv层
    expansion = 4

    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 = 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, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(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)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class detnet_bottleneck(nn.Module):
    # no expansion
    # dilation = 2
    # type B use 1x1 conv
    # 引入了空洞卷积，增加感受野

    def __init__(self, in_planes, planes, stride=1, block_type='A'):
        super(detnet_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=2, bias=False, dilation=2)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes)

        self.downsample = nn.Sequential()
        # 一个有序的容器，神经网络模块将按照在传入构造器的顺序依次被添加到计算图中执行，同时以神经网络模块为元素的有序字典也可以作为传入参数。
        if stride != 1 or in_planes != planes or block_type == 'B':
            self.downsample = nn.Sequential(
                nn.Conv2d(in_planes, planes, kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(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.downsample(x)
        out = F.relu(out)
        return out


class ResNet(nn.Module):
    # 以res50为例：model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
    # block = Bottleneck
    def __init__(self, block, layers, num_classes=1470):
        self.inplanes = 64
        super(ResNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 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)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        # self.layer5 = self._make_layer(block, 512, layers[3], stride=2)
        self.layer5 = self._make_detnet_layer(in_channels=2048)
        # self.avgpool = nn.AvgPool2d(14) #fit 448 input size
        # self.fc = nn.Linear(512 * block.expansion, num_classes)
        self.conv_end = nn.Conv2d(256, 30, kernel_size=3, stride=1, padding=1, bias=False)
        self.bn_end = nn.BatchNorm2d(30)
        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 _make_layer(self, block, planes, blocks, stride=1):
        # self.layer1 = self._make_layer(block, 64, layers[0])
        # 构建Resnet的conv2，其中conv2_1和2都是64通道，所以这边planes=64，blocks=3，共三层
        downsample = None
        if stride != 1 or self.inplanes != planes * block.expansion:
            # 如果s不等于1（说明输出与输入的尺寸不一致），或是通道数目不一致，那么需要在residual部分进行downsample使得两个tensor各尺寸一致
            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, stride, downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(self.inplanes, planes))

        return nn.Sequential(*layers)

    def _make_detnet_layer(self, in_channels):
        layers = []
        layers.append(detnet_bottleneck(in_planes=in_channels, planes=256, block_type='B'))
        layers.append(detnet_bottleneck(in_planes=256, planes=256, block_type='A'))
        layers.append(detnet_bottleneck(in_planes=256, planes=256, block_type='A'))
        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)
        x = self.layer3(x)
        x = self.layer4(x)
        x = self.layer5(x)
        # x = self.avgpool(x)
        # x = x.view(x.size(0), -1)
        # x = self.fc(x)
        x = self.conv_end(x)
        x = self.bn_end(x)
        x = torch.sigmoid(x)  # 归一化到0-1
        # x = x.view(-1,7,7,30)
        x = x.permute(0, 2, 3, 1)  # (-1,7,7,30)

        return x


def resnet18(pretrained=False, **kwargs):
    """Constructs a ResNet-18 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [2, 2, 2, 2], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet18']))
    return model


def resnet34(pretrained=False, **kwargs):
    """Constructs a ResNet-34 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(BasicBlock, [3, 4, 6, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet34']))
    return model


def resnet50(pretrained=False, **kwargs):
    """Constructs a ResNet-50 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 6, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet50']),strict=False)
    return model


def resnet101(pretrained=False, **kwargs):
    """Constructs a ResNet-101 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 4, 23, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet101']))
    return model


def resnet152(pretrained=False, **kwargs):
    """Constructs a ResNet-152 model.

    Args:
        pretrained (bool): If True, returns a model pre-trained on ImageNet
    """
    model = ResNet(Bottleneck, [3, 8, 36, 3], **kwargs)
    if pretrained:
        model.load_state_dict(model_zoo.load_url(model_urls['resnet152']))
    return model

def test():
    import torch
    from torch.autograd import Variable
    model = resnet50(pretrained=True)
    print(model)
    print(model.modules())
    img = torch.rand(2,3,224,224)
    img = Variable(img)
    output = model(img)
    print(output.size())

if __name__ == '__main__':
    test()