李沐笔记（NiN）

最新推荐文章于 2026-01-05 17:40:23 发布

原创最新推荐文章于 2026-01-05 17:40:23 发布 · 1.2k 阅读

0 ·

CC 4.0 BY-SA版权

文章标签：

#p2p #linq #tv

本文探讨了1*1卷积层如何在深度学习中起到全连接层的效果，深入理解其在神经网络中的作用。

1*1的卷积层相当于全连接层

import torch
from torch import nn
from d2l import torch as d2l


# NiN块
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())

# NiN模型
# 灰度图
net = nn.Sequential(nin_block(1,96,kernel_size=11,strides=4,padding=0),
                    nn.MaxPool2d(kernel_size=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(output_size)
                    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,tese_iter = d2l.load_data_fashion_mnist(batch_size,resize=224)
d2l.train_ch6(net,train_iter,test_iter,num_epochs,lr,d2l.try_gpu())