代码笔记21 Resnet backbone加载

仅作记录

  Resnet骨架的搭建与参数加载

import torch.nn as nn
import torch.utils.model_zoo as model_zoo

# Imagenet resnet
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, padding=1, stride=stride, bias=False)

class Resbackbone(nn.Module):
    def __init__(self):
        super(Resbackbone, self).__init__()
        self.backbone = 'resnet50'
        block = Bottleneck
        layers = [3, 4, 6, 3]

        # RGB encoder
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=64,
                               kernel_size=7, padding=3, stride=2, 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.inplanes = 64
        self.layer1 = self._make_layer(block, 64, layers[0], stride=1)
        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)



    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(in_channels=self.inplanes, out_channels=planes * block.expansion,
                          kernel_size=1, stride=stride, bias=False),
                nn.BatchNorm2d(planes * block.expansion))
        layers = []
        layers.append(block(inplanes=self.inplanes, planes=planes, stride=stride, downsample=downsample))
        self.inplanes = planes * block.expansion
        for i in range(1, blocks):
            layers.append(block(inplanes=self.inplanes, planes=planes))

        return nn.Sequential(*layers)

    def _load_resnet_pretrained(self):
        pretrain_dict = model_zoo.load_url(model_urls[self.backbone])
        model_dict = {}
        state_dict = self.state_dict()
        for name, para in pretrain_dict.items():
            if name in state_dict:
                if name.startswith('conv1'):
                    model_dict[name] = para
                elif name.startswith('bn1'):
                    model_dict[name] = para
                elif name.startswith('layer'):
                    model_dict[name] = para
        state_dict.update(model_dict)
        self.load_state_dict(state_dict)
        print('resnet {} paras loaded!'.format(self.backbone))


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=inplanes, out_channels=planes,
                               kernel_size=1, stride=1,bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(in_channels=planes, out_channels=planes,
                               kernel_size=3, stride=stride, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(in_channels=planes, out_channels=4 * planes,
                               kernel_size=1, stride=1, bias=False)
        self.bn3 = nn.BatchNorm2d(4 * planes)
        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 BasicBlock(nn.Module):
    expansion = 1

    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

if __name__ == '__main__':
    backbone = Resbackbone()
    backbone._load_resnet_pretrained()
    for name,para in backbone.state_dict(keep_vars=True).items():
        print(name,para.shape,para.requires_grad)