![](https://i-blog.csdnimg.cn/direct/3b1c9e73bf7240899c642999dc384e02.png)
全连接层在卷积后的第一个全连接层参数量太大,占用太多计算带宽
![](https://i-blog.csdnimg.cn/direct/073aec2c5f024c45a6bd73e04d6cb338.png)
取代全连接层:
![](https://i-blog.csdnimg.cn/direct/c23005afe37946d38a5c3512c484f80c.png)
![](https://i-blog.csdnimg.cn/direct/2ba59730138341c58cc8c10bc7f49dfc.png)
NiN网络结构
![](https://i-blog.csdnimg.cn/direct/0c7ace6313684866932de15b901a055e.png)
![](https://i-blog.csdnimg.cn/direct/68e5cb437e3b418992d9f96d0848fb20.png)
代码:
"""
网络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),
# 标签类别数是10
nin_block(384, 10, kernel_size=3, strides=1, padding=1),
nn.AdaptiveAvgPool2d((1, 1)),
# 将四维的输出转成二维的输出,其形状为(批量大小,10)
nn.Flatten())
X = torch.rand(size=(1, 1, 224, 224))
for layer in net:
X = layer(X)
print(layer.__class__.__name__,'output shape:\t', 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())
d2l.plt.show()