DL学习10-vggnet-mnist

最新推荐文章于 2025-05-17 22:15:01 发布

yy13138

最新推荐文章于 2025-05-17 22:15:01 发布

阅读量324

点赞数

分类专栏： DL学习文章标签：学习 pytorch 深度学习

本文链接：https://blog.youkuaiyun.com/qq_46102205/article/details/131483658

版权

DL学习专栏收录该内容

12 篇文章

订阅专栏

本文介绍了VGG网络的核心部分——VGGblock，它由多个卷积层加ReLU激活函数组成，通过MaxPool2d进行下采样。模型通过多个这样的块构建，最终使用Flatten层展平特征并接入全连接层进行分类。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

对于vgg而言，他最重要的是VGGblock，总的来说就是通过循环生成一个多conv加一个relu的block层，然后将其使用flatten进行拉伸，最后送入线形层。
话不多说，看代码。

class reshape_data(nn.Module):
    def forward(self,X):
        return X.view(-1,1,224,224)
        
def vgg_block(num_convs, in_channels, out_channels):
    layers = list()
    for _ in range(num_convs):
        layers.append(
            nn.Conv2d(in_channels,out_channels,kernel_size=3,padding=1))
        layers.append(nn.ReLU())
        in_channels = out_channels
    layers.append(nn.MaxPool2d(kernel_size=2,stride=2))
    return nn.Sequential(*layers)

模型结构定义

class Vggnet(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv_arch = ((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))
        self.net = self.vgg(self.conv_arch)
        self.reshape_data = reshape_data()

    def vgg(self,conv_arch):
        conv_bloks = list()
        in_channel = 1
        for (_num,outchannel) in self.conv_arch:
            conv_bloks.append(vgg_block(num_convs=_num,in_channels=in_channel,out_channels=outchannel))
            in_channel = outchannel
        return nn.Sequential(*conv_bloks,
                            nn.Flatten(),
                            nn.Linear(outchannel*7*7,4096),
                            nn.ReLU(),
                            nn.Dropout(.5),

                            nn.Linear(4096,4096),
                            nn.ReLU(),
                            nn.Dropout(.5),
                            nn.Linear(4096,10))

    def forward(self,X):
        X = self.reshape_data(X)
        output = self.net(X)
        return output

X = torch.rand(size=(1, 1, 224, 224), dtype=torch.float32)
net = Vggnet()
for layer in net.net:
    X = layer(X)
    print(layer.__class__.__name__,'output shape: \t',X.shape)

模型结构输出

Sequential output shape: 	 torch.Size([1, 64, 112, 112])
Sequential output shape: 	 torch.Size([1, 128, 56, 56])
Sequential output shape: 	 torch.Size([1, 256, 28, 28])
Sequential output shape: 	 torch.Size([1, 512, 14, 14])
Sequential output shape: 	 torch.Size([1, 512, 7, 7])
Flatten output shape: 	 torch.Size([1, 25088])
Linear output shape: 	 torch.Size([1, 4096])
ReLU output shape: 	 torch.Size([1, 4096])
Dropout output shape: 	 torch.Size([1, 4096])
Linear output shape: 	 torch.Size([1, 4096])
ReLU output shape: 	 torch.Size([1, 4096])
Dropout output shape: 	 torch.Size([1, 4096])
Linear output shape: 	 torch.Size([1, 10])