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

text
Python 开发环境最佳实践：Anaconda + Jupyter Notebook 快速上手指南

对于初学者而言，搭建一个高效稳定的 Python 开发环境是入门的关键一步。本文将详细介绍如何利用 Anaconda 和 Jupyter Notebook 来构建一个既易于管理又功能强大的开发环境。 ... [详细]

蜡笔小新 2024-11-21 18:30:23
int
Delphi XE2 之 FireMonkey 入门(19) - TFmxObject 的子类们(表)

td{border:1pxsolid#808080;}参考:和FMX相关的类(表)TFmxObjectIFreeNotification ... [详细]

蜡笔小新 2024-11-21 22:35:24
case
解决iOS应用推送通知错误：未找到有效aps-environment权限

在尝试加载支持推送通知的iOS应用程序的Ad Hoc构建时，遇到了‘no valid aps-environment entitlement found for application’的错误提示。本文将探讨此错误的原因及多种可能的解决方案。 ... [详细]

蜡笔小新 2024-11-21 19:26:31
int
Oracle 11g 创建表空间与基础配置

本文详细介绍了Oracle 11g中的创建表空间的方法，以及如何设置客户端和服务端的基本配置，包括用户管理、环境变量配置等。 ... [详细]

蜡笔小新 2024-11-21 18:54:39
int
ABAP开发者需关注的几大关键问题

长期从事ABAP开发工作的专业人士，在面对行业新趋势时，往往需要重新审视自己的发展方向。本文探讨了几位资深专家对ABAP未来走向的看法，以及开发者应如何调整技能以适应新的技术环境。 ... [详细]

蜡笔小新 2024-11-21 18:21:06
import
使用TabActivity实现Android顶部选项卡功能

本文介绍如何通过继承TabActivity来创建Android应用中的顶部选项卡。通过简单的步骤，您可以轻松地添加多个选项卡，并实现基本的界面切换功能。 ... [详细]

蜡笔小新 2024-11-21 17:47:42
tags
SIP基础概览

本文介绍了SIP（Session Initiation Protocol，会话发起协议）的基本概念、功能、消息格式及其实现机制。SIP是一种在IP网络上用于建立、管理和终止多媒体通信会话的应用层协议。 ... [详细]

蜡笔小新 2024-11-21 17:42:08
tags
Ryanair Expands Frankfurt Operations, Challenges Lufthansa's Dominance

Irish budget airline Ryanair announced plans to significantly increase its route network from Frankfurt Airport, marking a direct challenge to Lufthansa, Germany's leading carrier. ... [详细]

蜡笔小新 2024-11-21 13:09:01
tags
优化市场篮子分析性能

在执行市场篮子分析时遇到性能瓶颈，尤其是在设定频繁项集的支持度阈值为1%时。本文探讨了如何通过调整代码和参数来提高分析效率。 ... [详细]

蜡笔小新 2024-11-21 12:31:46
int
IC卡操作功能实现

本文介绍了如何通过C#语言调用动态链接库（DLL）中的函数来实现IC卡的基本操作，包括初始化设备、设置密码模式、获取设备状态等，并详细展示了将TextBox中的数据写入IC卡的具体实现方法。 ... [详细]

蜡笔小新 2024-11-21 11:02:19
int
OBS Studio自动化实践：利用脚本批量生成录制场景

本文探讨了如何利用OBS Studio进行高效录屏，并通过脚本实现场景的自动生成。适合对自动化办公感兴趣的读者。 ... [详细]

蜡笔小新 2024-11-21 10:44:53
int
spring boot使用jetty无法启动

spring boot使用jetty无法启动 ... [详细]

蜡笔小新 2024-11-21 10:15:52
int
入门指南：使用FastRPC技术连接Qualcomm Hexagon DSP

本文旨在为初学者提供关于如何使用FastRPC技术连接Qualcomm Hexagon DSP的基础知识。FastRPC技术允许开发者在本地客户端实现远程调用，从而简化Hexagon DSP的开发和调试过程。 ... [详细]

蜡笔小新 2024-11-21 10:03:34
int
[OReilly_Learning_Perl_5th_Edition]_Chap06_Exercises

3.[15]Writeaprogramtolistallofthekeysandvaluesin%ENV.PrinttheresultsintwocolumnsinASCIIbet ... [详细]

蜡笔小新 2024-11-20 18:28:56
int
【图像分类实战】利用DenseNet在PyTorch中实现秃头识别

本文详细介绍了如何使用DenseNet模型在PyTorch框架下实现秃头识别。首先，文章概述了项目所需的库和全局参数设置。接着，对图像进行预处理并读取数据集。随后，构建并配置DenseNet模型，设置训练和验证流程。最后，通过测试阶段验证模型性能，并提供了完整的代码实现。本文不仅涵盖了技术细节，还提供了实用的操作指南，适合初学者和有经验的研究人员参考。 ... [详细]

蜡笔小新 2024-11-06 15:21:35

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