转载:https://blog.csdn.net/whut_ldz/article/details/78874977?utm_source=copy
一、pytorch中的pre-train模型
import torchvision.models as models
#resnet
model = models.ResNet(pretrained=True)
model = models.resnet18(pretrained=True)
model = models.resnet34(pretrained=True)
model = models.resnet50(pretrained=True)
#vgg
model = models.VGG(pretrained=True)
model = models.vgg11(pretrained=True)
model = models.vgg16(pretrained=True)
model = models.vgg16_bn(pretrained=True)
二、预训练模型的修改
# coding=UTF-8
import torchvision.models as models
#调用模型
model = models.resnet50(pretrained=True)
#提取fc层中固定的参数
fc_features = model.fc.in_features
#修改类别为9
model.fc = nn.Linear(fc_features, 9)
2.增减卷积层
# coding=UTF-8
import torchvision.models as models
import torch
import torch.nn as nn
import math
import torch.utils.model_zoo as model_zoo
class CNN(nn.Module):
def __init__(self, block, layers, num_classes=9):
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.avgpool = nn.AvgPool2d(7, stride=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)
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)
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)
第三种方法
那么对于网络的修改怎样可以快速的去除model本身的网络层呢?
一个继承nn.module的model它包含一个叫做children()的函数,这个函数可以用来提取出model每一层的网络结构,在此基础上进行修改即可,修改方法如下(去除后两层):
resnet_layer = nn.Sequential(*list(model.children())[:-2])
那么,接下来就可以构建我们的网络了:
<code class="language-python">class Net(nn.Module):
def __init__(self , model):
super(Net, self).__init__()
#取掉model的后两层
self.resnet_layer = nn.Sequential(*list(model.children())[:-2])
self.transion_layer = nn.ConvTranspose2d(2048, 2048, kernel_size=14, stride=3)
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)
x = x.view(x.size(0), -1)
x = self.Linear_layer(x)
return x</code>
最后,构建一个对象,并加载resnet预训练的参数就可以啦~
resnet = models.resnet50(pretrained=True)
model = Net(resnet)