CNN

Code

以alexnet以及paddlepaddle框架为例

class AlexNet(fluid.dygraph.Layer):
    def __init__(self, num_classes=1):
        super(AlexNet, self).__init__()
        # num_channels相当于输入维度, num_filters相当于输出维度,
        # filter_size是卷积核尺寸, stride为滑动步长, padding为填充
        self.conv1 = Conv2D(num_channels=3, num_filters=96, filter_size=11, stride=4, padding=5, act='relu')
        self.pool1 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
        self.conv2 = Conv2D(num_channels=96, num_filters=256, filter_size=5, stride=1, padding=2, act='relu')
        self.pool2 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')
        self.conv3 = Conv2D(num_channels=256, num_filters=384, filter_size=3, stride=1, padding=1, act='relu')
        self.conv4 = Conv2D(num_channels=384, num_filters=384, filter_size=3, stride=1, padding=1, act='relu')
        self.conv5 = Conv2D(num_channels=384, num_filters=256, filter_size=3, stride=1, padding=1, act='relu')
        self.pool5 = Pool2D(pool_size=2, pool_stride=2, pool_type='max')

        self.fc1 = Linear(input_dim=12544, output_dim=4096, act='relu')
        self.drop_ratio1 = 0.5
        self.fc2 = Linear(input_dim=4096, output_dim=4096, act='relu')
        self.drop_ratio2 = 0.5
        self.fc3 = Linear(input_dim=4096, output_dim=num_classes)

    def forward(self, x):
        x = self.conv1(x)
        x = self.pool1(x)
        x = self.conv2(x)
        x = self.pool2(x)
        x = self.conv3(x)
        x = self.conv4(x)
        x = self.conv5(x)
        x = self.pool5(x)
        x = fluid.layers.reshape(x, [x.shape[0], -1])
        x = self.fc1(x)

        x = fluid.layers.dropout(x, self.drop_ratio1)
        x = self.fc2(x)
        x = fluid.layers.dropout(x, self.drop_ratio2)
        x = self.fc3(x)
        return x

with fluid.dygraph.guard():
    model = AlexNet()

术语解释

• 卷积核 num_filters
• 填充 padding
• 滑动步长 strides
• 通道数

卷积核

在飞桨中,num_channels为输入维度,num_filters为输出维度,filter_size为卷积核尺寸,

填充

填充主要是为了保证不丢失边缘数据,同时也应该注意填充尺寸不应过大,避免引入过多的无用数据

滑动步长

卷积核在输入的数据上会先沿着水平方向,再沿着垂直方向进行卷积操作,如果步长为1,name卷积核在水平方向上每操作一次,就向右移动一格,在进行下一次操作.卷积核中值为0的部分对最终结果没有贡献,但是他们也参与卷积

池化

池化主要用于降维同时保留关键特征

• 最大池化
• 平均池化
• 最小池化

步长为1的最大池化:

输出特征计算公式