pytorch實現squeezenet

squeezenet是16年發布的一款輕量級網絡模型，模型很小，只有4.8M，可用於移動設備，嵌入式設備。

關於squeezenet的原理可自行閱讀論文或查找博客，這里主要解讀下pytorch對squeezenet的官方實現。

地址：https://github.com/pytorch/vision/blob/master/torchvision/models/squeezenet.py

首先定義fire模塊，這是squeezenet的核心所在，降低3X3卷積的數量。

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)#定義壓縮層，1X1卷積
        self.squeeze_activation = nn.ReLU(inplace=True)
        self.expand1x1 = nn.Conv2d(squeeze_planes, expand1x1_planes,#定義擴展層，1X1卷積
                                   kernel_size=1)
        self.expand1x1_activation = nn.ReLU(inplace=True)
        self.expand3x3 = nn.Conv2d(squeeze_planes, expand3x3_planes,#定義擴展層，3X3卷積
                                   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)

可以看到首先定義壓縮層與兩個擴展層，壓縮層用的是1X1卷積，擴展層是1X1卷積和3X3卷積的混合使用，網絡inference的脈絡是先經過壓縮層，然后並行經過兩個擴展層，最后將擴展層串聯。

定義完核心模塊，來看網絡整體。

class SqueezeNet(nn.Module):

    def __init__(self, version=1.0, num_classes=1000):
        super(SqueezeNet, self).__init__()
        if version not in [1.0, 1.1]:
            raise ValueError("Unsupported SqueezeNet version {version}:"
                             "1.0 or 1.1 expected".format(version=version))
        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),
            )
        else:
            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),
            )
        # Final convolution is initialized differently form 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.AvgPool2d(13, stride=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 x.view(x.size(0), self.num_classes)

首先依然是定義網絡層，在這里有兩個版本，差別不大，都是fire模塊的堆積，最后經過全局平均池化輸出1000類。這里對卷積層采用了不同的初始化策略，我還沒仔細研究過，就不說了。