Pytorch学习笔记（I）——预训练模型（二）：修改网络结构（ResNet34及以下）
（pytorch1.0）最近在研究pytorch如何修改与训练模型的网络结构，然后发现了两种版本，一种是细调版，一种是快速版
经过一番钻研后发现细调版适合对网络模型进行大幅度的改动（如在原有的结构上穿插着增减层），而快速版适合直接对网络末端的层进行增减。
虽然快速版简单易懂，但是还是要对细调版有所了解才能比较，万一以后用的上呢。因此，我就好好研究了一番细调版，结果发现网上的代码或者博客基本都是相互搬运的，代码中的错误一模一样，对于我这种小白来说特别不友好。于是，我就在前人的基础上查缺补漏，重新整理了一下。
关于如何加载和使用，请查看前一篇博客Pytorch学习笔记（I）——预训练模型（一）：加载与使用
煎熬过了期末考试之后，终于开始全力科研了。
之前写过一篇Pytorch学习笔记（I）——预训练模型（二）：修改网络结构（ResNet50及以上）。最近再看resnet系列的网络结构时发现，不能笼统的用ResNet50代替全部，因为以34和50为分界，残差块的结构是不一样的。
区别在于，前者用的是基础模块BasicBlock（如下所示），后者用的是基础模块Bottleneck
所以再写一篇作为区分。
#定义一个3*3的卷积模板，步长为1，并且使用大小为1的zeropadding
def conv3x3(in_planes, out_planes, stride=1):
"3x3 convolution with padding"
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, bias=False)
#定义基础模块BasicBlock
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
话不多说，直接上代码，这里以resnet34为例
这一步必须参考原来的网络结构，从而定义一个类似的网络
import torchvision.models as models
import torch
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
#定义一个3*3的卷积模板，步长为1，并且使用大小为1的zeropadding
def conv3x3(in_planes, out_planes, stride=1):
"3x3 convolution with padding"
return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
padding=1, bias=False)
#定义基础模块BasicBlock
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
#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(512, 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
resnet34 = models.resnet34(pretrained=True)
#3 4 6 3 分别表示layer1 2 3 4 中BasicBlock模块的数量。res18则为2 2 2 2
cnn = CNN(BasicBlock, [3, 4, 6, 3])
# 读取参数
pretrained_dict = resnet34.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(resnet34)
print(cnn)
接下来我们来比对一下前后的变化。
1、 原来的resnet34最后两层信息如下
(avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
(fc): Linear(in_features=512, out_features=1000, bias=True)
2、 新的最后几层层信息如下
(avgpool): AdaptiveAvgPool2d(output_size=(1, 1))
(convtranspose1): ConvTranspose2d(2048, 2048, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
(maxpool2): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
(fclass): Linear(in_features=512, out_features=9, bias=True)
可以看出在最后一层fc被替换了。
如果想在中间进行增减，改变前向传播的顺序就好了