持續創作，加速成長！這是我參與「掘金日新計劃 · 6 月更文挑戰」的第10天，點擊查看活動詳情

 

🍊作者簡介：禿頭小蘇，致力於用最通俗的語言描述問題

🍊往期回顧：卡爾曼濾波系列1——卡爾曼濾波    基於pytorch搭建AlexNet神經網絡用於花類識別

🍊近期目標：擁有5000粉絲

🍊支持小蘇：點贊👍🏼、收藏⭐、留言📩

基於pytorch搭建GoogleNet神經網絡用於花類識別

寫在前面

  前面已經出過基於pytorch搭建AlexNet神經網絡用於花類識別和基於pytorch搭建VGGNet神經網絡用於花類識別的文章，建議閲讀此文章前先行閲讀前兩篇。

  這篇文章用到的網絡結構時GoogleNet，因此你需要對GoogleNet的結構有較清晰的瞭解，不清楚的戳此圖標☞☞☞瞭解詳情。

  和上一篇相同，本篇不會對實現花類識別的每一個步驟進行講解，只針對GoogleNet的網絡搭建細節進行闡述，大家可自行下載代碼進一步研究。

 

GoogleNet網絡模型搭建✨✨✨

  GoogleNet的結構乍一看還是挺複雜的，但是其中有大量的重複結構，即Inception結構。我們可以將Inception結構封裝成一個類在進行調用，這樣會大大提高代碼的可讀性。Inception類的定義如下：

```python class Inception(nn.Module): def init(self, in_channels, ch1x1, ch3x3red, ch3x3, ch5x5red, ch5x5, pool_proj): super(Inception, self).init()

    self.branch1 = BasicConv2d(in_channels, ch1x1, kernel_size=1)

    self.branch2 = nn.Sequential(
        BasicConv2d(in_channels, ch3x3red, kernel_size=1),
        BasicConv2d(ch3x3red, ch3x3, kernel_size=3, padding=1)   # 保證輸出大小等於輸入大小
    )

    self.branch3 = nn.Sequential(
        BasicConv2d(in_channels, ch5x5red, kernel_size=1),
        BasicConv2d(ch5x5red, ch5x5, kernel_size=5, padding=2)   # 保證輸出大小等於輸入大小
    )

    self.branch4 = nn.Sequential(
        nn.MaxPool2d(kernel_size=3, stride=1, padding=1),
        BasicConv2d(in_channels, pool_proj, kernel_size=1)
    )

def forward(self, x):
    branch1 = self.branch1(x)
    branch2 = self.branch2(x)
    branch3 = self.branch3(x)
    branch4 = self.branch4(x)

    outputs = [branch1, branch2, branch3, branch4]
    return torch.cat(outputs, 1)

```

  這裏我不想做過多的解釋，大家自己對照着GoogleNet的理論看應該也能很好的理解，但這裏我把這個類傳入的參數做一個簡單的解釋，其實就對應着Inception結構的一些參數，如下圖所示：

  這裏再談談BasicConv2d這個東東，這個其實也是我們定義的類，定義如下：

```python class BasicConv2d(nn.Module): def init(self, in_channels, out_channels, kwargs): super(BasicConv2d, self).init() self.conv = nn.Conv2d(in_channels, out_channels, kwargs) self.relu = nn.ReLU(inplace=True)

def forward(self, x):
    x = self.conv(x)
    x = self.relu(x)
    return x

```

  這個就更好理解了，其把卷積和後面的Relu激活封裝到了一起🥗🥗🥗

---

​  值得一提的是在GoogleNet網絡中，還存在着兩個結構相同的輔助分類器，為了簡化代碼，我們也將其封裝成類，如下：

```python class InceptionAux(nn.Module): def init(self, in_channels, num_classes): super(InceptionAux, self).init() self.averagePool = nn.AvgPool2d(kernel_size=5, stride=3) self.conv = BasicConv2d(in_channels, 128, kernel_size=1) # output[batch, 128, 4, 4]

    self.fc1 = nn.Linear(2048, 1024)
    self.fc2 = nn.Linear(1024, num_classes)

def forward(self, x):
    # aux1: N x 512 x 14 x 14, aux2: N x 528 x 14 x 14
    x = self.averagePool(x)
    # aux1: N x 512 x 4 x 4, aux2: N x 528 x 4 x 4
    x = self.conv(x)
    # N x 128 x 4 x 4
    x = torch.flatten(x, 1)
    x = F.dropout(x, 0.5, training=self.training)
    # N x 2048
    x = F.relu(self.fc1(x), inplace=True)
    x = F.dropout(x, 0.5, training=self.training)
    # N x 1024
    x = self.fc2(x)
    # N x num_classes
    return x

```

  這樣一切準備工作即已做好，我們就可以來定義我們的GoogleNet網絡了：

```python class GoogLeNet(nn.Module): def init(self, num_classes=1000, aux_logits=True): super(GoogLeNet, self).init() self.aux_logits = aux_logits

    self.conv1 = BasicConv2d(3, 64, kernel_size=7, stride=2, padding=3)
    self.maxpool1 = nn.MaxPool2d(3, stride=2, ceil_mode=True)   #ceil_mode=True表示求得的特徵為小數時，向上取整

    self.conv2 = BasicConv2d(64, 64, kernel_size=1)
    self.conv3 = BasicConv2d(64, 192, kernel_size=3, padding=1)
    self.maxpool2 = nn.MaxPool2d(3, stride=2, ceil_mode=True)

    self.inception3a = Inception(192, 64, 96, 128, 16, 32, 32)
    self.inception3b = Inception(256, 128, 128, 192, 32, 96, 64)
    self.maxpool3 = nn.MaxPool2d(3, stride=2, ceil_mode=True)

    self.inception4a = Inception(480, 192, 96, 208, 16, 48, 64)
    self.inception4b = Inception(512, 160, 112, 224, 24, 64, 64)
    self.inception4c = Inception(512, 128, 128, 256, 24, 64, 64)
    self.inception4d = Inception(512, 112, 144, 288, 32, 64, 64)
    self.inception4e = Inception(528, 256, 160, 320, 32, 128, 128)
    self.maxpool4 = nn.MaxPool2d(3, stride=2, ceil_mode=True)

    self.inception5a = Inception(832, 256, 160, 320, 32, 128, 128)
    self.inception5b = Inception(832, 384, 192, 384, 48, 128, 128)

    if self.aux_logits:
        self.aux1 = InceptionAux(512, num_classes)
        self.aux2 = InceptionAux(528, num_classes)

    self.avgpool = nn.AdaptiveAvgPool2d((1, 1))    #自適應的平均池化，將特質圖大小變成1x1
    self.dropout = nn.Dropout(0.4)
    self.fc = nn.Linear(1024, num_classes)
    if init_weights:
        self._initialize_weights()

def forward(self, x):
    # N x 3 x 224 x 224
    x = self.conv1(x)
    # N x 64 x 112 x 112
    x = self.maxpool1(x)
    # N x 64 x 56 x 56
    x = self.conv2(x)
    # N x 64 x 56 x 56
    x = self.conv3(x)
    # N x 192 x 56 x 56
    x = self.maxpool2(x)

    # N x 192 x 28 x 28
    x = self.inception3a(x)
    # N x 256 x 28 x 28
    x = self.inception3b(x)
    # N x 480 x 28 x 28
    x = self.maxpool3(x)
    # N x 480 x 14 x 14
    x = self.inception4a(x)
    # N x 512 x 14 x 14
    if self.training and self.aux_logits:    # eval model lose this layer
        aux1 = self.aux1(x)

    x = self.inception4b(x)
    # N x 512 x 14 x 14
    x = self.inception4c(x)
    # N x 512 x 14 x 14
    x = self.inception4d(x)
    # N x 528 x 14 x 14
    if self.training and self.aux_logits:    # eval model lose this layer
        aux2 = self.aux2(x)

    x = self.inception4e(x)
    # N x 832 x 14 x 14
    x = self.maxpool4(x)
    # N x 832 x 7 x 7
    x = self.inception5a(x)
    # N x 832 x 7 x 7
    x = self.inception5b(x)
    # N x 1024 x 7 x 7

    x = self.avgpool(x)
    # N x 1024 x 1 x 1
    x = torch.flatten(x, 1)
    # N x 1024
    x = self.dropout(x)
    x = self.fc(x)
    # N x 1000 (num_classes)
    if self.training and self.aux_logits:   # eval model lose this layer
        return x, aux2, aux1
    return x

```

 

注意事項

  這部分談談GoogleNet網絡模型搭建和使用的注意事項。我們知道在GoogleNet中有兩個輔助分類器，但這兩個輔助分類器是隻在訓練時使用的，測試時不使用。【測試時令參數self.training and self.aux_logits的值為False】由於訓練時使用了兩個輔助分類器，因此有三個輸出🍍🍍🍍

  在預測過程中，我們也不需要我們的輔助分類器，在加載模型參數時需要設置strict=False🍓🍓🍓

訓練結果展示

​  本篇文章不再詳細講解訓練步驟，和基於pytorch搭建AlexNet神經網絡用於花類識別基本一致。這裏展示一下訓練結果，如下圖所示：

  其準確率達到了0.742，我們可以再來看看我們保存的GoogleNet模型,如下圖，可以看出GoogleNet的參數相對於VGG可以説是少了許多許多，這和我們的理論部分也是契合的🥝🥝🥝

 

小結

  對於這一部分我強烈建議大家去使用Pycharm的調試功能，一步步的看每次運行的結果，這樣你會發現代碼結構特別的清晰。

參考視頻：http://www.bilibili.com/video/BV1r7411T7M5/?spm_id_from=333.788🌸🌸🌸

    如若文章對你有所幫助，那就🛴🛴🛴

咻咻咻咻~~duang\~~點個讚唄