【MXNet】（二十三）：实现GoogLeNet

论文原文《Going deeper with convolutions》。

GoogLeNet中的基础卷积块叫作Inception块，下图是一个Inception块的结构。

from mxnet import gluon, init, nd
from mxnet.gluon import nn

class Inception(nn.Block):
    def __init__(self, c1, c2, c3, c4, **kwargs):
        super(Inception, self).__init__(**kwargs)
        self.p1_1 = nn.Conv2D(c1, kernel_size=1, activation='relu')
        self.p2_1 = nn.Conv2D(c2[0], kernel_size=1, activation='relu')
        self.p2_2 = nn.Conv2D(c2[1], kernel_size=3, padding=1, activation='relu')
        self.p3_1 = nn.Conv2D(c3[0], kernel_size=1, activation='relu')
        self.p3_2 = nn.Conv2D(c3[1], kernel_size=5, padding=2, activation='relu')
        self.p4_1 = nn.MaxPool2D(pool_size=3, strides=1, padding=1)
        self.p4_2 = nn.Conv2D(c4, kernel_size=1, activation='relu')
        
    def forward(self, x):
        p1 = self.p1_1(x)
        p2 = self.p2_2(self.p2_1(x))
        p3 = self.p3_2(self.p3_1(x))
        p4 = self.p4_2(self.p4_1(x))
        return nd.concat(p1, p2, p3, p4, dim=1)

下面是GoogLeNet的主体部分。

b1 = nn.Sequential()
b1.add(nn.Conv2D(64, kernel_size=7, strides=2, padding=3, activation='relu'),
      nn.MaxPool2D(pool_size=3, strides=2, padding=1))

b2 = nn.Sequential()
b2.add(nn.Conv2D(64, kernel_size=1),
       nn.Conv2D(192, kernel_size=3, padding=1),
      nn.MaxPool2D(pool_size=3, strides=2, padding=1))

b3 = nn.Sequential()
b3.add(Inception(64, (96, 128),(16, 32), 32),
       Inception(128, (128, 192),(32, 96), 64),
      nn.MaxPool2D(pool_size=3, strides=2, padding=1))

b4 = nn.Sequential()
b4.add(Inception(192, (96, 208),(16, 48), 64),
       Inception(160, (112, 224),(24, 64), 64),
       Inception(128, (128, 256),(24, 64), 64),
       Inception(112, (144, 288),(32, 64), 64),
       Inception(256, (160, 320),(32, 128), 128),
      nn.MaxPool2D(pool_size=3, strides=2, padding=1))

b5 = nn.Sequential()
b5.add(Inception(256, (160, 320),(32, 128), 128),
       Inception(384, (192, 384),(48, 128), 128),
      nn.GlobalAvgPool2D())

net = nn.Sequential()
net.add(b1, b2, b3, b4, b5, nn.Dense(10))

构造一个输入看一下各层的尺寸。

X = nd.random.uniform(shape=(1, 1, 224, 224))
net.initialize(force_reinit=True)
for layer in net:
    X = layer(X)
    print(layer.name, 'output shape:\t', X.shape)

依然使用Fashion-MNIST数据集训练。

lr, num_epochs, batch_size, ctx = 0.1, 5, 64, try_gpu()
net.initialize(force_reinit=True, ctx=ctx, init=init.Xavier())
trainer = gluon.Trainer(net.collect_params(), 'sgd', {'learning_rate': lr})
train_iter, test_iter = load_data_fashion_mnist(batch_size, resize=224)
train(net, train_iter, test_iter, batch_size, trainer, ctx, num_epochs)

上面程序片段里的几个函数的实现请参考链接：【MXNet】（二十）：实现AlexNet。