VGG16迁移学习问题（只冻结前几个特征层）

Question

VGG16迁移学习问题
我把特征提取层冻结掉了，更改了全连接层做了训练，为了做对比，那现在我想只冻结前四个卷积块，把最后一个解冻和全连接层一起更改，应该要怎么写啊，求大虾们帮帮忙QAQ

import numpy as np
import pandas as pd
from sklearn.metrics import accuracy_score,confusion_matrix,classification_report
import matplotlib.pyplot as plt
import seaborn as sns
import hiddenlayer as hl

import torch
import torch.nn as nn
from torch.optim import SGD,Adam,RMSprop,Adagrad
import torch.utils.data as Data
from torchvision import models
from torchvision import transforms
from torchvision.datasets import ImageFolder

## 导入预训练好的VGG16网络
vgg16 = models.vgg16(pretrained=True)


## 获取vgg16的特征提取层
vgg = vgg16.features
# 将vgg16的特征提取层参数冻结，不对其进行更新
for param in vgg.parameters():
    param.requires_grad_(False)

## 使用VGG16的特征提取层＋新的全连接层组成新的网络
class MyVggModel(nn.Module):
    def __init__(self):
        super(MyVggModel,self).__init__()
        ## 预训练的vgg16的特征提取层
        self.vgg = vgg
        ## 添加新的全连接层
        self.classifier = nn.Sequential(
            nn.Linear(25088,512),
            nn.ReLU(),
            nn.Dropout(p=0.5),
            nn.Linear(512,256),
            nn.ReLU(),
            nn.Dropout(p=0.5),
            nn.Linear(256,4),
            nn.Softmax(dim=1)
        )
        

    ## 定义网络的向前传播路径   
    def forward(self, x):
        x = self.vgg(x)
        x = x.view(x.size(0), -1)
        output = self.classifier(x)
        return output
    
## 输出我们的网络结构
Myvggc = MyVggModel()
print(Myvggc)

MyVggModel(
(vgg): Sequential(
(0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(1): ReLU(inplace=True)
(2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(3): ReLU(inplace=True)
(4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(6): ReLU(inplace=True)
(7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(8): ReLU(inplace=True)
(9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(11): ReLU(inplace=True)
(12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(13): ReLU(inplace=True)
(14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(15): ReLU(inplace=True)
(16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(18): ReLU(inplace=True)
(19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(20): ReLU(inplace=True)
(21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(22): ReLU(inplace=True)
(23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
(24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(25): ReLU(inplace=True)
(26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(27): ReLU(inplace=True)
(28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
(29): ReLU(inplace=True)
(30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)
(classifier): Sequential(
(0): Linear(in_features=25088, out_features=512, bias=True)
(1): ReLU()
(2): Dropout(p=0.5, inplace=False)
(3): Linear(in_features=512, out_features=256, bias=True)
(4): ReLU()
(5): Dropout(p=0.5, inplace=False)
(6): Linear(in_features=256, out_features=4, bias=True)
(7): Softmax(dim=1)
)
)