pytorch识别CIFAR10：训练ResNet34（微调网络，准确率提升到85%）

作者：灬哭着说再见灬 | 来源：互联网 | 2023-08-28 12:00

在前一篇中的ResNet-34残差网络，经过训练准确率只达到80%。

这里对网络做点小修改，在最开始的卷积层中用更小（3*3）的卷积核，并且不缩小图片尺寸，相应的最后的平均池化的核改为4*4。

具体修改如下：

1 class ResNet34(nn.Module):
2 def __init__(self, block):
3 super(ResNet34, self).__init__()
4
5 # 初始卷积层核池化层
6 self.first = nn.Sequential(
7 # 卷基层1：3*3kernel，1stride，1padding，outmap：32-3+1*2 / 1 + 1，32*32
8 nn.Conv2d(3, 64, 3, 1, 1),
9 nn.BatchNorm2d(64),
10 nn.ReLU(inplace=True),
11
12 # 最大池化，3*3kernel，1stride（保持尺寸），1padding，
13 # outmap：32-3+2*1 / 1 + 1，32*32
14 nn.MaxPool2d(3, 1, 1)
15 )
16
17 # 第一层，通道数不变
18 self.layer1 = self.make_layer(block, 64, 64, 3, 1)
19
20 # 第2、3、4层，通道数*2，图片尺寸/2
21 self.layer2 = self.make_layer(block, 64, 128, 4, 2) # 输出16*16
22 self.layer3 = self.make_layer(block, 128, 256, 6, 2) # 输出8*8
23 self.layer4 = self.make_layer(block, 256, 512, 3, 2) # 输出4*4
24
25 self.avg_pool = nn.AvgPool2d(4) # 输出512*1
26 self.fc = nn.Linear(512, 10)

运行结果：

Files already downloaded and verified
ResNet34(
(first): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    (2): ReLU(inplace)
    (3): MaxPool2d(kernel_size=3, stride=1, padding=1, dilation=1, ceil_mode=False)
)
(layer1): Sequential(
    (0): ResBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (1): ResBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (2): ResBlock(
      (conv1): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
)
(layer2): Sequential(
    (0): ResBlock(
      (conv1): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(64, 128, kernel_size=(1, 1), stride=(2, 2))
        (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): ResBlock(
      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (2): ResBlock(
      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (3): ResBlock(
      (conv1): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
)
(layer3): Sequential(
    (0): ResBlock(
      (conv1): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(128, 256, kernel_size=(1, 1), stride=(2, 2))
        (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): ResBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (2): ResBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (3): ResBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (4): ResBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (5): ResBlock(
      (conv1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
)
(layer4): Sequential(
    (0): ResBlock(
      (conv1): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1))
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (downsample): Sequential(
        (0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2))
        (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      )
    )
    (1): ResBlock(
      (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
    (2): ResBlock(
      (conv1): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
      (relu): ReLU(inplace)
      (conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
      (bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
    )
)
(avg_pool): AvgPool2d(kernel_size=4, stride=4, padding=0)
(fc): Linear(in_features=512, out_features=10, bias=True)
)
one epoch spend: 0:00:55.832303
EPOCH:1, ACC:53.05

one epoch spend: 0:00:54.158082
EPOCH:2, ACC:61.94

......

one epoch spend: 0:00:54.178677
EPOCH:199, ACC:85.37

one epoch spend: 0:00:53.657917
EPOCH:200, ACC:85.25

CIFAR10 pytorch ResNet34 Train: EPOCH:200, BATCH_SZ:128, LR:0.1, ACC:85.38
train spend time: 3:11:21.618257

运行200个迭代，每个迭代耗时54秒，准确率提升了5%，达到85%。准确率变化曲线如下：

推荐阅读

function
JavaScript在网页设计中的嵌入应用方法是什么

本篇内容主要讲解“JavaScript在网页设计中的嵌入应用方法是什么”，感兴趣的朋友不妨来看看。本文介绍的方法操作简单快捷，实用性强。下面就让小 ... [详细]

蜡笔小新 2024-09-28 12:59:54
bit
42VERSE & 圆圈徽章，Web3 社交的流派之争——针对两个国内案例的调研

01 行业分析本文所研究的细分赛道为：Web3应用层——社交与内容场景——DID/创新场景（以元宇宙3D空间为 ... [详细]

蜡笔小新 2024-09-29 12:10:23
web
python打卡记录去重_Python零基础学习笔记与记录之一（了解Python这个小伙伴）

本人学习笔记，知识点均摘自于网络，用于学习和交流(如未注明出处，请提醒，将及时更正，谢谢)OS:我学习是为了上 ... [详细]

蜡笔小新 2023-10-17 16:05:58
web
S3D算法详解

S3D论文详解论文地址：RethinkingSpatiotemporalFeatureLearning:Speed-AccuracyTrade-offsinVide ... [详细]

蜡笔小新 2023-10-16 17:45:39
web
navicat生成er图_实践案例丨ACL2020 KBQA 基于查询图生成回答多跳复杂问题

摘要：目前复杂问题包括两种：含约束的问题和多跳关系问题。本文对ACL2020KBQA基于查询图生成的方法来回答多跳复杂问题这一论文工作进行了解读 ... [详细]

蜡笔小新 2023-10-16 15:31:07
bit
Android 自定义控件基础 canvas paint

1、首先说一下canvas类：ClassOverviewTheCanvasclassholdsthedrawcalls.Todrawsomething,youne ... [详细]

蜡笔小新 2024-09-30 07:06:19
bit
C#学习教程：使用RSACryptoServiceProvider进行公钥加密分享

使用RSACryptoServiceProvider进行公钥加密我已经在CodeProject上发表了一篇文章，解释了如何使用RSA提供程序进行加密和解密：RSA私钥加密虽然200 ... [详细]

蜡笔小新 2024-09-29 18:06:38
audio
java播放mp3格式音乐_java播放mp3格式音频文件

下载完成之后解压提取jl1.0.0.1.jar这里写图片描述将jl1.0.0.1.jar拷贝到项目中，并添加到Library这里写图片描述4.源代码Tip:由于工程名 ... [详细]

蜡笔小新 2024-09-29 17:28:42
function
ajax自动加载列表页,jQuery+ajax实现滚动到页面底部自动加载图文列表效果(类似图片懒加载)...

本文实例讲述了jQueryajax实现滚动到页面底部自动加载图文列表效果。分享给大家供大家参考，具体如下：phttp:www.w3.orgTRxht ... [详细]

蜡笔小新 2024-09-29 14:45:53
function
删除数组中的第一级标识符。 - Remove first levels of identifier in array

Ithinkthishasbeenupbefore,butcouldntfindanyanswertoit.Ifitsalreadyansweredplease ... [详细]

蜡笔小新 2024-09-29 12:47:47
import
《每个设计师都应该掌握的50个css代码段》11~20段

2019独角兽企业重金招聘Python工程师标准11.胶卷边框img.polaroid{background:#000;*Changethistoabackgroundima ... [详细]

蜡笔小新 2024-09-29 11:18:42
case
使用大小映射和density2d的不寻常的图例 - Unusual legend using size mapping and density2d

Iamtryingtomakeascatterplotinggplot2withasizemappingtoathirdvariableanddensity2dc ... [详细]

蜡笔小新 2024-09-29 10:40:17
settings
谁有主板上(BOIS主板设置)所有的英文翻译成中文后的意思？

来设定CPU工作相关参数　　POWERMANAGEMENTSETUP（省电功能设定）　　用来设定CPU、硬盘、显示器等等设备的省电功能　　PNP/PCICONFIGURATION（即插即用设备与 ... [详细]

蜡笔小新 2024-09-29 10:36:45
function
配置OracleACFS集群文件系统

配置OracleACFS集群文件系统 2012-07-1010:18:39标签：asmacfs版权声明：原创作品，谢绝转载！否则将追究法律责任。 ... [详细]

蜡笔小新 2024-09-28 16:33:10
case
2019 年 Firebase 峰会上发布的新功能

作者FrancisMa,HeadofProductFirebase的使命是帮助移动开发者和Web开发者迈向成功，但考虑到Firebase每个月有超过200万个活跃的应 ... [详细]

蜡笔小新 2024-09-28 08:07:01

灬哭着说再见灬

这个家伙很懒，什么也没留下！

Tags | 热门标签

RankList | 热门文章