1、全连接层的问题
-
卷积层需要较少的参数
-
但是卷积层后的第一个全连接层的参数
参数过多带来的问题:
- 会占用很多内存
- 容易过拟合
2、NiN块
两个1X1的卷积层代替全连接,1x1可以看作是全连接层
3、NiN架构
4、总结
5、实现NiN
import torch
from torch import nn
from d2l import torch as d2l
def nin_block(in_channels, out_channels, kernel_size, strides, padding):
return nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size, strides, 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, strides=4, padding=0),
nn.MaxPool2d(3, stride=2),
nin_block(96, 256, kernel_size=5, strides=1, padding=2),
nn.MaxPool2d(3, stride=2),
nin_block(256, 384, kernel_size=3, strides=1, padding=1),
nn.MaxPool2d(3, stride=2), nn.Dropout(0.5),
nin_block(384, 10, kernel_size=3, strides=1, padding=1),
nn.AdaptiveAvgPool2d((1, 1)),
nn.Flatten())
#开始训练
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())