J9 - Inception v3算法

原创

已于 2024-04-19 14:54:34 修改 · 1.2k 阅读

11 ·

CC 4.0 BY-SA版权

文章标签：

#算法 #深度学习 #机器学习 #人工智能 #神经网络 #计算机视觉 #cnn

于 2024-03-15 12:32:44 首次发布

🍨 本文为🔗365天深度学习训练营中的学习记录博客

🍖 原作者：K同学啊

理论知识

InceptionV3版本是2015年发布的，InceptionV1的第三个版本。
V3版本的特点如下：

更深层的网络：具有48层卷积层，这使得网络可以提取更多层次的特征。
Factorized Convolution(分解卷积)：使用分解卷积，将大卷积核替换为多个小的卷积核，进一步降低了参数量，减少了计算的复杂度，保持良好的性能
使用了BatchNormalization：V3版本在每个卷积层后都加了BN层，使模型更容易收敛并提升泛化能力。BN层的使用可以减少Internal covariate shift （内部协变量偏移），提高模型的训练速度，提升模型的鲁棒性。
辅助分类器：V3版本引入了辅助分类器，在模型的中间引出一些特征构建辅助分类器，将辅助分类器的输出与主分类器的输出加权融合，得到最终的预测结果
RMSProp优化器：V3版本的Inception使用了RMSProp优化器，可以自适应的调节学习率，使训练过程更加稳定，收敛更快。

模型结构

InceptionV1版本中，作者将卷积通过1x1卷积降维后进行大卷积核计算，降低了计算量。在InceptionV3版本中继续做了改进。

首先是将大核卷积改为多层小核卷积，比如把一个5x5的卷积变成两个3x3的卷积。虽然由一层变成了两层，但是一个5x5卷积的开销是1个3x3的2.78倍，所以这种改变仍有利于性能的提升。
其次是将NxN的卷积变为1xN + Nx1的两个卷积。3x3的卷积变成1x3 +3x1的卷积，可以节省33%的性能。

串行会让网络变的很深，可能会造成信息损失。因此InceptionV3采用了并行的拆解

最终模型的结构为：

模型实现

首先是InceptionA模块，和InceptionV1一样

class InceptionA(nn.Module):
    def __init__(self, in_channels, pool_features):
        super().__init__()
        
        self.branch1x1 = BasicConv2d(in_channels, 64, kernel_size=1)

        self.branch5x5_1 = BasicConv2d(in_channels, 48, kernel_size=1)
        self.branch5x5_2 = BasicConv2d(48, 64, kernel_size=5, padding=2)

        self.branch3x3_1 = BasicConv2d(in_channels, 64, kernel_size=1)
        self.branch3x3_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
        self.branch3x3_3 = BasicConv2d(96, 96, kernel_size=3, padding=1)

        self.branch_pool = BasicConv2d(in_channels, pool_features, kernel_size=1)
    def forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch5x5 = self.branch5x5_1(x)
        branch5x5 = self.branch5x5_2(branch5x5)

        branch3x3 = self.branch3x3_1(x)
        branch3x3 = self.branch3x3_2(branch3x3)
        branch3x3 = self.branch3x3_3(branch3x3)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch5x5, branch3x3, branch_pool]
        return torch.cat(outputs, 1)

然后是InceptionB模块，串行拆分大卷积核

class InceptionB(nn.Module):
    def __init__(self, in_channels, channels_7x7):
        super().__init__()

        self.branch1x1 = BasicConv2d(in_channels, 192, kernel_size=1)

        c7 = channels_7x7
        self.branch7x7_1 = BasicConv2d(in_channels, c7, kernel_size=1)
        self.branch7x7_2 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3))
        self.branch7x7_3 = BasicConv2d(c7, 192, kernel_size=(7, 1), padding=(3, 0))

        self.branch7x7dbl_1 = BasicConv2d(in_channels, c7, kernel_size=1)
        self.branch7x7dbl_2 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0))
        self.branch7x7dbl_3 = BasicConv2d(c7, c7, kernel_size=(1, 7), padding=(0, 3))
        self.branch7x7dbl_4 = BasicConv2d(c7, c7, kernel_size=(7, 1), padding=(3, 0))
        self.branch7x7dbl_5 = BasicConv2d(c7, 192, kernel_size=(1, 7), padding=(0, 3))

        self.branch_pool = BasicConv2d(in_channels, 192, kernel_size=1)

    def forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch7x7 = self.branch7x7_1(x)
        branch7x7 = self.branch7x7_2(branch7x7)
        branch7x7 = self.branch7x7_3(branch7x7)

        branch7x7dbl = self.branch7x7dbl_1(x)
        branch7x7dbl = self.branch7x7dbl_2(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_3(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_4(branch7x7dbl)
        branch7x7dbl = self.branch7x7dbl_5(branch7x7dbl)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch7x7, branch7x7dbl, branch_pool]
        return torch.cat(outputs, 1)

然后是InceptionC,并行拆分大卷积核

class InceptionC(nn.Module):
    def __init__(self, in_channels):
        super().__init__()
        
        self.branch1x1 = BasicConv2d(in_channels, 320, kernel_size=1)

        self.branch3x3_1 = BasicConv2d(in_channels, 384, kernel_size=1)
        self.branch3x3_2a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1))
        self.branch3x3_2b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0))

        self.branch3x3dbl_1 = BasicConv2d(in_channels, 448, kernel_size=1)
        self.branch3x3dbl_2 = BasicConv2d(448, 384, kernel_size=3, padding=1)
        self.branch3x3dbl_3a = BasicConv2d(384, 384, kernel_size=(1, 3), padding=(0, 1))
        self.branch3x3dbl_3b = BasicConv2d(384, 384, kernel_size=(3, 1), padding=(1, 0))

        self.branch_pool = BasicConv2d(in_channels, 192, kernel_size=1)

    def forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch3x3 = self.branch3x3_1(x)
        branch3x3 = [self.branch3x3_2a(branch3x3), self.branch3x3_2b(branch3x3)]
        branch3x3 = torch.cat(branch3x3, 1)

        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = [self.branch3x3dbl_3a(branch3x3dbl), self.branch3x3dbl_3b(branch3x3dbl)]
        branch3x3dbl = torch.cat(branch3x3dbl, 1)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch3x3, branch3x3dbl, branch_pool]
        return torch.cat(outputs, 1)

还有用于降维的Reduction模块

class ReductionA(nn.Module):
    def __init__(self, in_channels):
        super().__init__()
        
        self.branch3x3 = BasicConv2d(in_channels, 384, kernel_size=3, stride=2)

        self.branch3x3dbl_1 = BasicConv2d(in_channels, 64, kernel_size=1)
        self.branch3x3dbl_2 = BasicConv2d(64, 96, kernel_size=3, padding=1)
        self.branch3x3dbl_3 = BasicConv2d(96, 96, kernel_size=3, stride=2)

    def forward(self, x):
        branch3x3 = self.branch3x3(x)

        branch3x3dbl = self.branch3x3dbl_1(x)
        branch3x3dbl = self.branch3x3dbl_2(branch3x3dbl)
        branch3x3dbl = self.branch3x3dbl_3(branch3x3dbl)

        branch_pool = F.max_pool2d(x, kernel_size=3, stride=2)

        outputs = [branch3x3, branch3x3dbl, branch_pool]
        return torch.cat(outputs, 1)

class ReductionB(nn.Module):
    def __init__(self, in_channels):
        super().__init__()

        self.branch3x3_1 = BasicConv2d(in_channels, 192, kernel_size=1)
        self.branch3x3_2 = BasicConv2d(192, 320, kernel_size=3, stride=2)

        self.branch7x7x3_1 = BasicConv2d(in_channels, 192, kernel_size=1)
        self.branch7x7x3_2 = BasicConv2d(192, 192