卷积神经网络（六）---实现 cifar10 分类

        cifar10 数据集有60000张图片，每张图片的大小都是 32x32 的三通道的彩色图，一共是10种类别、每种类别有6000张图片，如图4.27所示。

图 4.27  cifar数据集

        使用前面讲过的残差结构来处理 cifar10 数据集，可以实现比较高的准确率。

        首先进行图像增强，使用前面介绍的增强方式。

train_transform = transforms.Compose([
    transforms.Scale(40),
    transforms.RandomHorizontalFlip(),
    transforms.RandomCrop(32),
    transforms.ToTensor(),
    transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])

test_transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])
])

        注意只对训练图片进行图像增强，提高其泛化能力，对于测试集，仅对其中心化，不做其他的图像增强。

        下面先定义好 resnet 的基本模块。

def conv3x3(in_channels, out_channels, stride=1):
    return nn.Conv2d(
        in_channels,
        out_channels,
        kernel_size=3,
        stride=stride,
        padding=1,
        bias=False
    )


# Residual Block
class ResidualBlock(nn.Module):
    def __init__(self, in_channels, out_channels, stride=1, downsample=None):
        super(ResidualBlock, self).__init__()
        self.conv1 = conv3x3(in_channels, out_channels, stride)
        self.bn1 = nn.BatchNorm2d(out_channels)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(out_channels, out_channels)
        self.bn2 = nn.BatchNorm2d(out_channels)
        self.downsample = downsample

    def forward(self, x):
        residual = x
        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)
        out = self.bn2(out)
        if self.downsample:
            residual = self.downsample(x)
        out += residual
        out = self.relu(out)
        return out

        和前面介绍的内容一样，先定义残差模块，再将残差模块拼接起来，注意其中的维度变化。

class ResNet(nn.Module):
    def __init__(self, block, layers, num_classes=10):
        super(ResNet, self).__init__()
        self.in_channels = 16
        self.conv = conv3x3(3, 16)
        self.bn = nn.BatchNorm2d(16)
        self.relu = nn.ReLU(inplace=True)
        self.layer1 = self.make_layer(block, 16, layers[0])
        self.layer2 = self.make_layer(block, 32, layers[0], 2)
        self.layer3 = self.make_layer(block, 64, layers[0], 2)
        self.avg_pool = nn.AvgPool2d(8)
        self.fc = nn.Linear(64, num_classes)

    def make_layer(self, block, out_channels, blocks, stride=1):
        downsample = None
        if (stride != 1) or (self.in_channels != out_channels):
            downsample = nn.Sequential(
                conv3x3(self.in_channels, out_channels, stride=stride),
                nn.BatchNorm2d(out_channels)
            )
        layers = [block(self.in_channels, out_channels, stride, downsample)]
        self.in_channels = out_channels
        for i in range(1, blocks):
            layers.append(block(out_channels, out_channels))
        return nn.Sequential(*layers)

    def foward(self, x):
        out = self.conv(x)
        out = self.bn(out)
        out = self.relu(out)
        out = self.layer1(out)
        out = self.layer2(out)
        out = self.layer3(out)
        out = self.avg_pool(out)
        out = out.view(out.size(0), -1)
        out = self.fc(out)
        return out

        最后在 cifar10 的数据集上跑100个 epoch，实现66.61%的训练集准确率，68%的验证集准确率，因为这里只跑了100次，所以还有一定的提升空间。同时使用更深的残差和更多的训练技巧能实现更好的实验结果，如图4.28所示。

        因为这里我是按照自己的想法写的普通版本的 cifar10 分类识别，所以准确率最后并不是很高，如果有人读懂了上面的方法，可以进行试一试。