赋予模型权重的方法-01（redefined network）

系列文章目录

本文介绍了如何把别人的网络改为自己的

---

一、快速版（vgg16为例）

把最后两层改成自己需要的模型

代码如下（示例）：

# import torchvision.models as models
# import torch
# import torch.nn as nn

# class Net(nn.Module):
#     def __init__(self, model):
#         super(Net, self).__init__()
#         # -2表示去掉model的后两层
#         self.vgg_layer = nn.Sequential(*list(model.children())[:-2])
#         self.transion_layer = nn.ConvTranspose2d(2048, 2048, kernel_size=14, stride=3)  反卷积
#         self.pool_layer = nn.MaxPool2d(32)
#         self.Linear_layer = nn.Linear(2048, 8)

#     def forward(self, x):
#         x = self.resnet_layer(x)
#         x = self.transion_layer(x)
#         x = self.pool_layer(x)
#         #将一个多行的Tensor,拼接成一行,-1指在不告诉函数有多少列
#         x = x.view(x.size(0), -1)
#         x = self.Linear_layer(x)
#         return x

# vgg = models.vgg16(pretrained=True)
# model = Net(vgg)

二、细调版

此示例为自己定义网络结构，并生成权重。 然后用resnet50的权重升级一下自己的权重 代码如下（示例）：

import torchvision.models as models
import torch
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo

#Bottleneck是一个class 里面定义了使用1*1的卷积核进行降维跟升维的一个残差块，可以在github resnet pytorch上查看 
#先1*1卷积降维，3*3卷积不变维，1*1卷积升维（4倍）
class Bottleneck(nn.Module):
    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

#不做修改的层不能乱取名字，否则预训练的权重参数无法传入
class CNN(nn.Module):

    def __init__(self, block, layers, num_classes=9):
        self.inplanes = 64
        super(CNN, 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.avgpool = nn.AdaptiveAvgPool2d(output_size=(1,1))
        # 新增一个反卷积层
        self.convtranspose1 = nn.ConvTranspose2d(2048, 2048, kernel_size=3, stride=1, padding=1, output_padding=0,
                                                  groups=1, bias=False, dilation=1)
        # # 新增一个最大池化层
        self.maxpool2 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
        # # 去掉原来的fc层，新增一个fclass层
        # self.fclass = nn.Linear(2048, 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 _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),
                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)
	#这一步用以设置前向传播的顺序，可以自行调整，前提是合理
    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.avgpool(x)
        # 新加层的forward
        # x = x.view(x.size(0), -1)
        x = self.convtranspose1(x)
        x = self.maxpool2(x)
        # x = x.view(x.size(0), -1)
        # x = self.fclass(x)

        return x


# 加载model
resnet50 = models.resnet50(pretrained=True)
#3 4 6 3 分别表示layer1 2 3 4 中Bottleneck模块的数量。res101则为3 4 23 3 
cnn = CNN(Bottleneck, [3, 4, 6, 3])
# # 读取参数
pretrained_dict = resnet50.state_dict()
model_dict = cnn.state_dict()
# # 将pretrained_dict里不属于model_dict的键剔除掉
pretrained_dict = {k: v for k, v in pretrained_dict.items() if k in model_dict}
# # 更新现有的model_dict
model_dict.update(pretrained_dict)
# # 加载我们真正需要的state_dict
cnn.load_state_dict(model_dict)
# print(resnet50)
# print(cnn)

input = torch.rand(2,3,512,512)
out = cnn(input)

三。删除模型最后一层

list(model.modules()) # to inspect the modules of your model

my_model = nn.Sequential(*list(model.modules())[:-1]) # strips off last linear layer

所以我在代码中添加了如下代码行：model = models.resnet152(pretrained=True)

list(model.modules()) # to inspect the modules of your model

my_model = nn.Sequential(*list(model.modules())[:-1]) # strips off last linear layer

print(my_model)