论文要点：NiN（模型M+公式F+代码C）

# Network In Network (NiN)

论文：Network In Network by Min Lin1,2, Qiang Chen2, Shuicheng Yan

1. 模型

图片来源：动手学深度学习 by 李沐

2. 代码

# 代码来自动手学深度学习 by 李沐
# 实现NiN
import torch
from torch import nn
from d2l import torch as d2l

def nin_block(in_channels, out_channels, kernel_size, stride, padding):
    return nn.Sequential(nn.Conv2d(in_channels, out_channels, kernel_size, stride, padding),
                         nn.ReLU(),
                         nn.Conv2d(out_channels, out_channels, kernel_size=1),
                         nn.ReLU(),
                         nn.Conv2d(out_channels, out_channels, kernel_size=1),
                         nn.ReLU()
                        )

net = nn.Sequential(nin_block(1, 96, kernel_size=11, stride=4, padding=0),
                    nn.MaxPool2d(3, stride=2),
                    nin_block(96, 256, kernel_size=5, stride=1, padding=2),
                    nn.MaxPool2d(3, stride=2),
                    nin_block(256, 384, kernel_size=3, stride=1, padding=1),
                    nn.MaxPool2d(3, stride=2),
                    nn.Dropout(0.5),
                    nin_block(384, 10, kernel_size=3, stride=1, padding=1),
                    nn.AdaptiveAvgPool2d((1, 1)),  #全局池化层，指定输出大小
                    nn.Flatten()
                   )

X = torch.rand((1, 1, 224, 224), dtype=torch.float32)
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__, 'output shape:', X.shape)

lr, num_epochs, batch_size = 0.1, 10, 128
train_iter, test_iter = d2l.load_data_fashion_mnist(batch_size, resize=224)
d2l.train_ch6(net, train_iter, test_iter, num_epochs, lr, d2l.try_gpu())