SqueezeNet 神经网络简介与代码实战

最新推荐文章于 2024-07-29 00:43:43 发布

AI街潜水的八角

最新推荐文章于 2024-07-29 00:43:43 发布

阅读量155

点赞数

分类专栏：深度学习CNN模型实战文章标签：神经网络深度学习人工智能

本文链接：https://blog.csdn.net/m0_59023219/article/details/130832152

版权

深度学习CNN模型实战专栏收录该内容

18 篇文章 1 订阅

订阅专栏

SqueezeNet是一种轻量级的深度学习模型，2016年提出，以较少的参数实现AlexNet级别的精度。其核心是FireModule，包含1x1和3x3卷积的squeeze与expand层。模型特点是使用1x1卷积减少参数量，通过调整网络结构提高效率。提供的PyTorch代码展示了SqueezeNet的构建过程。

摘要由CSDN通过智能技术生成

1.介绍
SqueezeNet是2016提出的，虽然比较老，但也有值得学习的地方，比如通过1x1的卷积来减少 feature map 的维数，更加详细的介绍可以参见：SQUEEZENET: ALEXNET-LEVEL ACCURACY WITH 50X FEWER PARAMETERS AND <0.5MB MODEL SIZE

2.模型结构
SqueezeNet 的核心在于 Fire module，Fire module 由两层构成，分别是 squeeze 层+expand 层，如下图 1 所示，squeeze 层是一个 1*1 卷积核的卷积层，expand 层是 1*1 和 3*3 卷积核的卷积层，expand 层中，把 1*1 和 3*3 得到的 feature map 进行 concat。

3.模型特点

（1）使用1∗1卷积代替3∗3 卷积：参数减少为原来的1/9
（2）减少输入通道数量：这一部分使用squeeze layers来实现
（3）将池化层操作延后，可以给卷积层提供更大的激活图：更大的激活图保留了更多的信息，可以提供更高的分类准确率

4.代码实现 pytorch

class Fire(nn.Module):
 
    def __init__(self, inplanes, squeeze_planes,
                 expand1x1_planes, expand3x3_planes):
        super(Fire, self).__init__()
        self.inplanes = inplanes
        self.squeeze = nn.Conv2d(inplanes, squeeze_planes, kernel_size=1)
        self.squeeze_activation = nn.ReLU(inplace=True)
        self.expand1x1 = nn.Conv2d(squeeze_planes, expand1x1_planes,
                                   kernel_size=1)
        self.expand1x1_activation = nn.ReLU(inplace=True)
        self.expand3x3 = nn.Conv2d(squeeze_planes, expand3x3_planes,
                                   kernel_size=3, padding=1)
        self.expand3x3_activation = nn.ReLU(inplace=True)
 
    def forward(self, x):
        x = self.squeeze_activation(self.squeeze(x))
        return torch.cat([
            self.expand1x1_activation(self.expand1x1(x)),
            self.expand3x3_activation(self.expand3x3(x))
        ], 1)
 
 
class SqueezeNet(nn.Module):
 
    def __init__(self, version='1_0', num_classes=1000):
        super(SqueezeNet, self).__init__()
        self.num_classes = num_classes
        if version == '1_0':
            self.features = nn.Sequential(
                nn.Conv2d(3, 96, kernel_size=7, stride=2),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(96, 16, 64, 64),
                Fire(128, 16, 64, 64),
                Fire(128, 32, 128, 128),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(256, 32, 128, 128),
                Fire(256, 48, 192, 192),
                Fire(384, 48, 192, 192),
                Fire(384, 64, 256, 256),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(512, 64, 256, 256),
            )
        elif version == '1_1':
            self.features = nn.Sequential(
                nn.Conv2d(3, 64, kernel_size=3, stride=2),
                nn.ReLU(inplace=True),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(64, 16, 64, 64),
                Fire(128, 16, 64, 64),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(128, 32, 128, 128),
                Fire(256, 32, 128, 128),
                nn.MaxPool2d(kernel_size=3, stride=2, ceil_mode=True),
                Fire(256, 48, 192, 192),
                Fire(384, 48, 192, 192),
                Fire(384, 64, 256, 256),
                Fire(512, 64, 256, 256),
            )
        else:
            # FIXME: Is this needed? SqueezeNet should only be called from the
            # FIXME: squeezenet1_x() functions
            # FIXME: This checking is not done for the other models
            raise ValueError("Unsupported SqueezeNet version {version}:"
                             "1_0 or 1_1 expected".format(version=version))
 
        # Final convolution is initialized differently from the rest
        final_conv = nn.Conv2d(512, self.num_classes, kernel_size=1)
        self.classifier = nn.Sequential(
            nn.Dropout(p=0.5),
            final_conv,
            nn.ReLU(inplace=True),
            nn.AdaptiveAvgPool2d((1, 1))
        )
 
        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                if m is final_conv:
                    init.normal_(m.weight, mean=0.0, std=0.01)
                else:
                    init.kaiming_uniform_(m.weight)
                if m.bias is not None:
                    init.constant_(m.bias, 0)
 
    def forward(self, x):
        x = self.features(x)
        x = self.classifier(x)
        return torch.flatten(x, 1)