【深度学习】使用自己写的VGG16网络训练精度不提升

Question

本人根据VGG16的模型自己写了个VGG16的网络，但是用它进行训练的时候，精度一直不变，换用pytorch官方的VGG16就精度会从低到高变化，所以感觉问题不在我的训练方法上，请问我这个网络模型哪里有问题吗？下面是网络代码

import torch
from torch import nn


class MyVGG16(nn.Module):
    def __init__(self, class_number):
        super(MyVGG16, self).__init__()
        self.block1 = nn.Sequential(
            nn.Conv2d(in_channels=3, out_channels=64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(inplace=True),
            nn.Conv2d(in_channels=64, out_channels=64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
        )
        self.block2 = nn.Sequential(
            nn.Conv2d(in_channels=64, out_channels=128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(in_channels=128, out_channels=128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1)
        )
        self.block3 = nn.Sequential(
            nn.Conv2d(in_channels=128, out_channels=256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(in_channels=256, out_channels=256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(in_channels=256, out_channels=256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1),
        )
        self.block4 = nn.Sequential(
            nn.Conv2d(256, 512, kernel_size=(3,3), padding=1),
            nn.ReLU(),
            nn.Conv2d(512, 512, kernel_size=(3,3), padding=1),
            nn.ReLU(),
            nn.Conv2d(512, 512, kernel_size=(3,3), padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2, padding=0),
        )
        self.block4 = nn.Sequential(
            nn.Conv2d(in_channels=256, out_channels=512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(in_channels=512, out_channels=512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(in_channels=512, out_channels=512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1),
        )
        self.block5 = nn.Sequential(
            nn.Conv2d(in_channels=512, out_channels=512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(in_channels=512, out_channels=512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.Conv2d(in_channels=512, out_channels=512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1),
        )
        self.block6 = nn.Sequential(
            nn.Flatten(),
            nn.Linear(in_features=512 * 7 * 7, out_features=4096),
            nn.ReLU(),
            nn.Dropout(p=0.5, inplace=False),
            nn.Linear(in_features=4096, out_features=4096),
            nn.ReLU(),
            nn.Dropout(p=0.5, inplace=False),
            nn.Linear(in_features=4096, out_features=1000),
             
            # 因为这是一个class_number分类问题，所以输出class_number
            nn.Linear(1000, class_number),
            
            # UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
            # 加上dim消除警告
            nn.Softmax(dim=1)
        )

    def forward(self, input):
        output = self.block1(input)
        output = self.block2(output)
        output = self.block3(output)
        output = self.block4(output)
        output = self.block5(output)
        output = self.block6(output)
        return output

Answer 1

删除最后的softmax层，在内个relu之前加归一化就好了