首页
所有分类
TAGS
文字工具 EMOJI BIBLE
编程 Python

使用PyTorch实现MNIST手写体识别代码

Posted in Python onJanuary 18, 2020

实验环境

win10 + anaconda + jupyter notebook

Pytorch1.1.0

Python3.7

gpu环境（可选）

MNIST数据集介绍

MNIST 包括6万张28x28的训练样本，1万张测试样本，可以说是CV里的“Hello Word”。本文使用的CNN网络将MNIST数据的识别率提高到了99%。下面我们就开始进行实战。

导入包

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
torch.__version__

定义超参数 

BATCH_SIZE=512
EPOCHS=20 
DEVICE = torch.device("cuda" if torch.cuda.is_available() else "cpu")

数据集

我们直接使用PyTorch中自带的dataset，并使用DataLoader对训练数据和测试数据分别进行读取。如果下载过数据集这里download可选择False

train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('data', train=True, download=True, 
            transform=transforms.Compose([
              transforms.ToTensor(),
              transforms.Normalize((0.1307,), (0.3081,))
            ])),
    batch_size=BATCH_SIZE, shuffle=True)

test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('data', train=False, transform=transforms.Compose([
              transforms.ToTensor(),
              transforms.Normalize((0.1307,), (0.3081,))
            ])),
    batch_size=BATCH_SIZE, shuffle=True)

定义网络

该网络包括两个卷积层和两个线性层，最后输出10个维度，即代表0-9十个数字。

class ConvNet(nn.Module):
  def __init__(self):
    super().__init__()
    self.conv1=nn.Conv2d(1,10,5) # input:(1,28,28) output:(10,24,24) 
    self.conv2=nn.Conv2d(10,20,3) # input:(10,12,12) output:(20,10,10)
    self.fc1 = nn.Linear(20*10*10,500)
    self.fc2 = nn.Linear(500,10)
  def forward(self,x):
    in_size = x.size(0)
    out = self.conv1(x)
    out = F.relu(out)
    out = F.max_pool2d(out, 2, 2) 
    out = self.conv2(out)
    out = F.relu(out)
    out = out.view(in_size,-1)
    out = self.fc1(out)
    out = F.relu(out)
    out = self.fc2(out)
    out = F.log_softmax(out,dim=1)
    return out

实例化网络 

model = ConvNet().to(DEVICE) # 将网络移动到gpu上
optimizer = optim.Adam(model.parameters()) # 使用Adam优化器

定义训练函数

def train(model, device, train_loader, optimizer, epoch):
  model.train()
  for batch_idx, (data, target) in enumerate(train_loader):
    data, target = data.to(device), target.to(device)
    optimizer.zero_grad()
    output = model(data)
    loss = F.nll_loss(output, target)
    loss.backward()
    optimizer.step()
    if(batch_idx+1)%30 == 0: 
      print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
        epoch, batch_idx * len(data), len(train_loader.dataset),
        100. * batch_idx / len(train_loader), loss.item()))

定义测试函数

def test(model, device, test_loader):
  model.eval()
  test_loss = 0
  correct = 0
  with torch.no_grad():
    for data, target in test_loader:
      data, target = data.to(device), target.to(device)
      output = model(data)
      test_loss += F.nll_loss(output, target, reduction='sum').item() # 将一批的损失相加
      pred = output.max(1, keepdim=True)[1] # 找到概率最大的下标
      correct += pred.eq(target.view_as(pred)).sum().item()

  test_loss /= len(test_loader.dataset)
  print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
    test_loss, correct, len(test_loader.dataset),
    100. * correct / len(test_loader.dataset)))

开始训练 

for epoch in range(1, EPOCHS + 1):
  train(model, DEVICE, train_loader, optimizer, epoch)
  test(model, DEVICE, test_loader)

实验结果 

Train Epoch: 1 [14848/60000 (25%)]	Loss: 0.375058
Train Epoch: 1 [30208/60000 (50%)]	Loss: 0.255248
Train Epoch: 1 [45568/60000 (75%)]	Loss: 0.128060

Test set: Average loss: 0.0992, Accuracy: 9690/10000 (97%)

Train Epoch: 2 [14848/60000 (25%)]	Loss: 0.093066
Train Epoch: 2 [30208/60000 (50%)]	Loss: 0.087888
Train Epoch: 2 [45568/60000 (75%)]	Loss: 0.068078

Test set: Average loss: 0.0599, Accuracy: 9816/10000 (98%)

Train Epoch: 3 [14848/60000 (25%)]	Loss: 0.043926
Train Epoch: 3 [30208/60000 (50%)]	Loss: 0.037321
Train Epoch: 3 [45568/60000 (75%)]	Loss: 0.068404

Test set: Average loss: 0.0416, Accuracy: 9859/10000 (99%)

Train Epoch: 4 [14848/60000 (25%)]	Loss: 0.031654
Train Epoch: 4 [30208/60000 (50%)]	Loss: 0.041341
Train Epoch: 4 [45568/60000 (75%)]	Loss: 0.036493

Test set: Average loss: 0.0361, Accuracy: 9873/10000 (99%)

Train Epoch: 5 [14848/60000 (25%)]	Loss: 0.027688
Train Epoch: 5 [30208/60000 (50%)]	Loss: 0.019488
Train Epoch: 5 [45568/60000 (75%)]	Loss: 0.018023

Test set: Average loss: 0.0344, Accuracy: 9875/10000 (99%)

Train Epoch: 6 [14848/60000 (25%)]	Loss: 0.024212
Train Epoch: 6 [30208/60000 (50%)]	Loss: 0.018689
Train Epoch: 6 [45568/60000 (75%)]	Loss: 0.040412

Test set: Average loss: 0.0350, Accuracy: 9879/10000 (99%)

Train Epoch: 7 [14848/60000 (25%)]	Loss: 0.030426
Train Epoch: 7 [30208/60000 (50%)]	Loss: 0.026939
Train Epoch: 7 [45568/60000 (75%)]	Loss: 0.010722

Test set: Average loss: 0.0287, Accuracy: 9892/10000 (99%)

Train Epoch: 8 [14848/60000 (25%)]	Loss: 0.021109
Train Epoch: 8 [30208/60000 (50%)]	Loss: 0.034845
Train Epoch: 8 [45568/60000 (75%)]	Loss: 0.011223

Test set: Average loss: 0.0299, Accuracy: 9904/10000 (99%)

Train Epoch: 9 [14848/60000 (25%)]	Loss: 0.011391
Train Epoch: 9 [30208/60000 (50%)]	Loss: 0.008091
Train Epoch: 9 [45568/60000 (75%)]	Loss: 0.039870

Test set: Average loss: 0.0341, Accuracy: 9890/10000 (99%)

Train Epoch: 10 [14848/60000 (25%)]	Loss: 0.026813
Train Epoch: 10 [30208/60000 (50%)]	Loss: 0.011159
Train Epoch: 10 [45568/60000 (75%)]	Loss: 0.024884

Test set: Average loss: 0.0286, Accuracy: 9901/10000 (99%)

Train Epoch: 11 [14848/60000 (25%)]	Loss: 0.006420
Train Epoch: 11 [30208/60000 (50%)]	Loss: 0.003641
Train Epoch: 11 [45568/60000 (75%)]	Loss: 0.003402

Test set: Average loss: 0.0377, Accuracy: 9894/10000 (99%)

Train Epoch: 12 [14848/60000 (25%)]	Loss: 0.006866
Train Epoch: 12 [30208/60000 (50%)]	Loss: 0.012617
Train Epoch: 12 [45568/60000 (75%)]	Loss: 0.008548

Test set: Average loss: 0.0311, Accuracy: 9908/10000 (99%)

Train Epoch: 13 [14848/60000 (25%)]	Loss: 0.010539
Train Epoch: 13 [30208/60000 (50%)]	Loss: 0.002952
Train Epoch: 13 [45568/60000 (75%)]	Loss: 0.002313

Test set: Average loss: 0.0293, Accuracy: 9905/10000 (99%)

Train Epoch: 14 [14848/60000 (25%)]	Loss: 0.002100
Train Epoch: 14 [30208/60000 (50%)]	Loss: 0.000779
Train Epoch: 14 [45568/60000 (75%)]	Loss: 0.005952

Test set: Average loss: 0.0335, Accuracy: 9897/10000 (99%)

Train Epoch: 15 [14848/60000 (25%)]	Loss: 0.006053
Train Epoch: 15 [30208/60000 (50%)]	Loss: 0.002559
Train Epoch: 15 [45568/60000 (75%)]	Loss: 0.002555

Test set: Average loss: 0.0357, Accuracy: 9894/10000 (99%)

Train Epoch: 16 [14848/60000 (25%)]	Loss: 0.000895
Train Epoch: 16 [30208/60000 (50%)]	Loss: 0.004923
Train Epoch: 16 [45568/60000 (75%)]	Loss: 0.002339

Test set: Average loss: 0.0400, Accuracy: 9893/10000 (99%)

Train Epoch: 17 [14848/60000 (25%)]	Loss: 0.004136
Train Epoch: 17 [30208/60000 (50%)]	Loss: 0.000927
Train Epoch: 17 [45568/60000 (75%)]	Loss: 0.002084

Test set: Average loss: 0.0353, Accuracy: 9895/10000 (99%)

Train Epoch: 18 [14848/60000 (25%)]	Loss: 0.004508
Train Epoch: 18 [30208/60000 (50%)]	Loss: 0.001272
Train Epoch: 18 [45568/60000 (75%)]	Loss: 0.000543

Test set: Average loss: 0.0380, Accuracy: 9894/10000 (99%)

Train Epoch: 19 [14848/60000 (25%)]	Loss: 0.001699
Train Epoch: 19 [30208/60000 (50%)]	Loss: 0.000661
Train Epoch: 19 [45568/60000 (75%)]	Loss: 0.000275

Test set: Average loss: 0.0339, Accuracy: 9905/10000 (99%)

Train Epoch: 20 [14848/60000 (25%)]	Loss: 0.000441
Train Epoch: 20 [30208/60000 (50%)]	Loss: 0.000695
Train Epoch: 20 [45568/60000 (75%)]	Loss: 0.000467

Test set: Average loss: 0.0396, Accuracy: 9894/10000 (99%)

总结

一个实际项目的工作流程：找到数据集，对数据做预处理，定义我们的模型，调整超参数，测试训练，再通过训练结果对超参数进行调整或者对模型进行调整。

以上这篇使用PyTorch实现MNIST手写体识别代码就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持三水点靠木。

使用PyTorch实现MNIST手写体识别代码

- Author -

kaijie234

声明：登载此文出于传递更多信息之目的，并不意味着赞同其观点或证实其描述。

Python 相关文章推荐
Python 返回汉字的汉语拼音
Feb 27 Python
列举Python中吸引人的一些特性
Apr 09 Python
Python中使用不同编码读写txt文件详解
May 28 Python
利用python程序生成word和PDF文档的方法
Feb 14 Python
对python文件读写的缓冲行为详解
Feb 13 Python
在Python文件中指定Python解释器的方法
Feb 18 Python
使用Python做定时任务及时了解互联网动态
May 15 Python
python实现各种插值法(数值分析)
Jul 30 Python
什么是Python中的顺序表
Jun 02 Python
Python爬虫抓取指定网页图片代码实例
Jul 24 Python
Python面向对象特殊属性及方法解析
Sep 16 Python
Python字节单位转换(将字节转换为K M G T)
Mar 02 Python
Pytorch之finetune使用详解
Jan 18 #Python
pytorch 修改预训练model实例
Jan 18 #Python
Pytorch自己加载单通道图片用作数据集训练的实例
Jan 18 #Python
pyinstaller 3.6版本通过pip安装失败的解决办法(推荐)
Jan 18 #Python
Python实现点云投影到平面显示
Jan 18 #Python
Pytorch 实现计算分类器准确率(总分类及子分类)
Jan 18 #Python
在pytorch 中计算精度、回归率、F1 score等指标的实例
Jan 18 #Python
防火墙(2) IIS(7) 远程登录(2) https(7) Windows server 2019(5) http(6) Windows server 2008(5) 远程控制(1) Telnet(1) Windows server 2016(6)
You might like
如何使用PHP实现javascript的escape和unescape函数
2013/06/29 PHP
改写函数实现PHP二维/三维数组转字符串
2013/09/13 PHP
PHP开发中AJAX技术的简单应用
2015/12/11 PHP
Laravel 验证码认证学习记录小结
2019/12/20 PHP
禁止JQuery中的load方法装载IE缓存中文件的方法
2009/09/11 Javascript
JavaScript 事件系统
2010/07/22 Javascript
通过DOM脚本去设置样式信息
2010/09/19 Javascript
javascript中类的定义及其方式(《javascript高级程序设计》学习笔记)
2011/07/04 Javascript
js父窗口关闭时子窗口随之关闭完美解决方案
2014/04/29 Javascript
jquery处理json对象
2014/11/03 Javascript
AngularJS Select(选择框)使用详解
2017/01/18 Javascript
js 调用百度分享功能
2017/02/27 Javascript
基于Particles.js制作超炫粒子动态背景效果(仿知乎)
2017/09/13 Javascript
解决angular2 获取到的数据无法实时更新的问题
2018/08/31 Javascript
nodejs一个简单的文件服务器的创建方法
2019/09/13 NodeJs
Python中文字符串截取问题
2015/06/15 Python
对Python进行数据分析_关于Package的安装问题
2017/05/22 Python
python实现识别手写数字 python图像识别算法
2020/03/23 Python
Odoo中如何生成唯一不重复的序列号详解
2018/02/10 Python
python通过Windows下远程控制Linux系统
2018/06/20 Python
使用python读取.text文件特定行的数据方法
2019/01/28 Python
解决IDEA 的 plugins 搜不到任何的插件问题
2020/05/04 Python
Python延迟绑定问题原理及解决方案
2020/08/04 Python
python 基于opencv实现图像增强
2020/12/23 Python
法国美发器材和产品购物网站：Beauty Coiffure
2016/12/05 全球购物
享誉全球的多元化时尚精品购物平台：Farfetch发发奇（支持中文）
2017/08/08 全球购物
发现世界上最好的珠宝设计师：JewelStreet
2017/12/17 全球购物
后勤副校长自我鉴定
2013/10/13 职场文书
目标管理责任书
2014/04/15 职场文书
实验室标语
2014/06/21 职场文书
夫妻婚内购房协议书
2014/10/05 职场文书
集团财务总监岗位职责
2015/04/03 职场文书
科级干部培训心得体会
2016/01/06 职场文书
python如何在word中存储本地图片
2021/04/07 Python
「偶像大师 MILLION LIVE！」七尾百合子手办开订
2022/03/21 日漫
Mysql使用全文索引(FullText index)的实例代码
2022/04/03 MySQL