李沐-动手学深度学习NiN

最新推荐文章于 2024-10-02 01:49:36 发布

永恒的溪流

最新推荐文章于 2024-10-02 01:49:36 发布

阅读量142

点赞数 2

分类专栏：李沐-动手学深度学习文章标签：深度学习人工智能

本文链接：https://blog.csdn.net/zslgoup1484/article/details/141368630

版权

李沐-动手学深度学习专栏收录该内容

24 篇文章 0 订阅

订阅专栏

一.NiN的由来-改进过程及思想

·全连接层的问题：内存带宽过拟合

二.NiN框架学习

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())

#创建一个数据样本来查看每个块的输出形状。
X = torch.rand(size=(1,1,224,224))
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__,'output shape:\t',X.shape)

三.模型训练

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)), #全局平均池化，尺寸变成1x1
    #将四维的输出转成二维的输出，其形状为（批量大小，10）
    nn.Flatten())#直接消掉1x1

'''
#创建一个数据样本来查看每个块的输出形状。
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()