Python 10 训练模型
原文：https://www.cnblogs.com/denny402/p/7520063.html
原文：https://www.jianshu.com/p/84f72791806f
原文：https://blog.csdn.net/lee813/article/details/89609691
1、下载fashion-mnist数据集
地址：https://github.com/zalandoresearch/fashion-mnist
下面这四个都要下载，下载完成后，解压到同一个目录，我是解压到“E:/fashion_mnist/”这个目录里面，好和下面的代码目录一致
2、在Geany中执行下面这段代码。
这段代码里面，需要先用pip安装skimage、torch、torchvision，前两篇文章有安装步骤。
这段代码的作用：将下载下来的 二进制文件 转换为 图片，会在目录中生成两个文件夹和两个文本。
文件夹里面全是图片，图片的内容是数字，N多数字。
文本的内容主要是图片和真实数字的一个关联。
import os
from skimage import io
import torchvision.datasets.mnist as mnist root="E:/fashion_mnist/"
train_set = (
mnist.read_image_file(os.path.join(root, 'train-images-idx3-ubyte')),
mnist.read_label_file(os.path.join(root, 'train-labels-idx1-ubyte'))
)
test_set = (
mnist.read_image_file(os.path.join(root, 't10k-images-idx3-ubyte')),
mnist.read_label_file(os.path.join(root, 't10k-labels-idx1-ubyte'))
)
print("training set :",train_set[0].size())
print("test set :",test_set[0].size()) def convert_to_img(train=True):
if(train):
f=open(root+'train.txt','w')
data_path=root+'/train/'
if(not os.path.exists(data_path)):
os.makedirs(data_path)
for i, (img,label) in enumerate(zip(train_set[0],train_set[1])):
img_path=data_path+str(i)+'.jpg'
io.imsave(img_path,img.numpy())
f.write(img_path+' '+str(label)+'\n')
f.close()
else:
f = open(root + 'test.txt', 'w')
data_path = root + '/test/'
if (not os.path.exists(data_path)):
os.makedirs(data_path)
for i, (img,label) in enumerate(zip(test_set[0],test_set[1])):
img_path = data_path+ str(i) + '.jpg'
io.imsave(img_path, img.numpy())
f.write(img_path + ' ' + str(label) + '\n')
f.close() convert_to_img(True)
convert_to_img(False)
3、原文的这段代码编译会出错，主要是跟下载的数据有关，数据格式不一样，这里还在处理，原因是找到了的，就一个int的转换，下面贴出改过后的代码
出错的地方：
import torch
import re
import numpy
from torch.autograd import Variable
from torchvision import transforms
from torch.utils.data import Dataset, DataLoader
from PIL import Image
root="E:/fashion_mnist/" def default_loader(path):
return Image.open(path).convert('RGB')
class MyDataset(Dataset):
def __init__(self, txt, transform=None, target_transform=None, loader=default_loader):
fh = open(txt, 'r')
imgs = []
for line in fh:
line = line.strip('\n')
line = line.rstrip()
words = line.split()
p1 = re.compile(r'[(](.*?)[)]', re.S)
arr = re.findall(p1, words[1])
word = arr[0]
imgs.append((words[0],int(word)))
self.imgs = imgs
self.transform = transform
self.target_transform = target_transform
self.loader = loader def __getitem__(self, index):
fn, label = self.imgs[index]
img = self.loader(fn)
if self.transform is not None:
img = self.transform(img)
return img,label def __len__(self):
return len(self.imgs) train_data=MyDataset(txt=root+'train.txt', transform=transforms.ToTensor())
test_data=MyDataset(txt=root+'test.txt', transform=transforms.ToTensor())
train_loader = DataLoader(dataset=train_data, batch_size=64, shuffle=True)
test_loader = DataLoader(dataset=test_data, batch_size=64)
3、原文的代码，还有一部分也会报错，ERROR如下。
唉，感叹一下，下次还是看一下语法那些，能读懂了代码再改吧，本想怎个拿来主义的，结果拿来了还是不能运行
解决-原文地址：https://blog.csdn.net/weixin_43848267/article/details/88874584
解决：将 loss_return.data[0] 改为 loss_return.data
还有几个地方 也要将 .data[0] 改为 .data
4、可完整运行的代码
代码1：
import os
from skimage import io
import torchvision.datasets.mnist as mnist root="E:/fashion_mnist/"
train_set = (
mnist.read_image_file(os.path.join(root, 'train-images-idx3-ubyte')),
mnist.read_label_file(os.path.join(root, 'train-labels-idx1-ubyte'))
)
test_set = (
mnist.read_image_file(os.path.join(root, 't10k-images-idx3-ubyte')),
mnist.read_label_file(os.path.join(root, 't10k-labels-idx1-ubyte'))
)
print("training set :",train_set[0].size())
print("test set :",test_set[0].size()) def convert_to_img(train=True):
if(train):
f=open(root+'train.txt','w')
data_path=root+'/train/'
if(not os.path.exists(data_path)):
os.makedirs(data_path)
for i, (img,label) in enumerate(zip(train_set[0],train_set[1])):
img_path=data_path+str(i)+'.jpg'
io.imsave(img_path,img.numpy())
f.write(img_path+' '+str(label)+'\n')
f.close()
else:
f = open(root + 'test.txt', 'w')
data_path = root + '/test/'
if (not os.path.exists(data_path)):
os.makedirs(data_path)
for i, (img,label) in enumerate(zip(test_set[0],test_set[1])):
img_path = data_path+ str(i) + '.jpg'
io.imsave(img_path, img.numpy())
f.write(img_path + ' ' + str(label) + '\n')
f.close() convert_to_img(True)
convert_to_img(False)
代码2：
import re
import numpy
import torch
from torch.autograd import Variable
from torchvision import transforms
from torch.utils.data import Dataset, DataLoader
from PIL import Image
root="E:/fashion_mnist/" # -----------------ready the dataset--------------------------
def default_loader(path):
return Image.open(path).convert('RGB')
class MyDataset(Dataset):
def __init__(self, txt, transform=None, target_transform=None, loader=default_loader):
fh = open(txt, 'r')
imgs = []
for line in fh:
line = line.strip('\n')
line = line.rstrip()
words = line.split() p1 = re.compile(r'[(](.*?)[)]', re.S)
arr = re.findall(p1, words[1])
word = arr[0] imgs.append((words[0],int(word)))
self.imgs = imgs
self.transform = transform
self.target_transform = target_transform
self.loader = loader def __getitem__(self, index):
fn, label = self.imgs[index]
img = self.loader(fn)
if self.transform is not None:
img = self.transform(img)
return img,label def __len__(self):
return len(self.imgs) train_data=MyDataset(txt=root+'train.txt', transform=transforms.ToTensor())
test_data=MyDataset(txt=root+'test.txt', transform=transforms.ToTensor())
train_loader = DataLoader(dataset=train_data, batch_size=64, shuffle=True)
test_loader = DataLoader(dataset=test_data, batch_size=64) #-----------------create the Net and training------------------------ class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = torch.nn.Sequential(
torch.nn.Conv2d(3, 32, 3, 1, 1),
torch.nn.ReLU(),
torch.nn.MaxPool2d(2))
self.conv2 = torch.nn.Sequential(
torch.nn.Conv2d(32, 64, 3, 1, 1),
torch.nn.ReLU(),
torch.nn.MaxPool2d(2)
)
self.conv3 = torch.nn.Sequential(
torch.nn.Conv2d(64, 64, 3, 1, 1),
torch.nn.ReLU(),
torch.nn.MaxPool2d(2)
)
self.dense = torch.nn.Sequential(
torch.nn.Linear(64 * 3 * 3, 128),
torch.nn.ReLU(),
torch.nn.Linear(128, 10)
) def forward(self, x):
conv1_out = self.conv1(x)
conv2_out = self.conv2(conv1_out)
conv3_out = self.conv3(conv2_out)
res = conv3_out.view(conv3_out.size(0), -1)
out = self.dense(res)
return out model = Net()
print(model) optimizer = torch.optim.Adam(model.parameters())
loss_func = torch.nn.CrossEntropyLoss() for epoch in range(10):
print('epoch {}'.format(epoch + 1))
# training-----------------------------
train_loss = 0.
train_acc = 0.
for batch_x, batch_y in train_loader:
batch_x, batch_y = Variable(batch_x), Variable(batch_y)
out = model(batch_x)
loss = loss_func(out, batch_y)
train_loss += loss.item()
pred = torch.max(out, 1)[1]
train_correct = (pred == batch_y).sum()
train_acc += train_correct.item() optimizer.zero_grad()
loss.backward()
optimizer.step()
print('Train Loss: {:.6f}, Acc: {:.6f}'.format(train_loss / (len(
train_data)), train_acc / (len(train_data)))) # evaluation--------------------------------
model.eval()
eval_loss = 0.
eval_acc = 0.
for batch_x, batch_y in test_loader:
batch_x, batch_y = Variable(batch_x), Variable(batch_y)
out = model(batch_x)
loss = loss_func(out, batch_y)
eval_loss += loss.item()
pred = torch.max(out, 1)[1]
num_correct = (pred == batch_y).sum()
eval_acc += num_correct.item()
print('Test Loss: {:.6f}, Acc: {:.6f}'.format(eval_loss / (len(
test_data)), eval_acc / (len(test_data))))
5、总结
提示：训练模型有点耗时，这里注意一下
图片如果过小，标签页里面单独打开图片会大些，排版搞得屁理解一下，一来没时间写文章，二来排版还没学，以后空了就会学。还是先把文章的质量提高了来
出现的问题主要是因为 torch的版本不同造成的，所以一会我把 我这里的环境贴出来，避免发生同样的错误。
6、环境
系统：win7 64位
Python 3.7.3
各个包的版本号，其它的好像就没啥了
可测试代码-版本2
代码1：
#coding=utf-8 import os
from skimage import io
import torchvision.datasets.mnist as mnist root="E:/fashion_mnist/"
train_set = (
mnist.read_image_file(os.path.join(root, 'train-images-idx3-ubyte')),
mnist.read_label_file(os.path.join(root, 'train-labels-idx1-ubyte'))
)
test_set = (
mnist.read_image_file(os.path.join(root, 't10k-images-idx3-ubyte')),
mnist.read_label_file(os.path.join(root, 't10k-labels-idx1-ubyte'))
)
print("training set :",train_set[0].size())
print("test set :",test_set[0].size()) def convert_to_img(train=True):
if(train):
f=open(root+'train.txt','w')
data_path=root+'/train/'
if(not os.path.exists(data_path)):
os.makedirs(data_path)
for i, (img,label) in enumerate(zip(train_set[0],train_set[1])):
img_path=data_path+str(i)+'.jpg'
io.imsave(img_path,img.numpy())
f.write(img_path+' '+str(label.numpy())+'\n') # label改为label.numpy()
f.close()
else:
f = open(root + 'test.txt', 'w')
data_path = root + '/test/'
if (not os.path.exists(data_path)):
os.makedirs(data_path)
for i, (img,label) in enumerate(zip(test_set[0],test_set[1])):
img_path = data_path+ str(i) + '.jpg'
io.imsave(img_path, img.numpy())
f.write(img_path + ' ' + str(label.numpy()) + '\n')
f.close() convert_to_img(True)
convert_to_img(False)
代码2：
import torch
from torch.autograd import Variable
from torchvision import transforms
from torch.utils.data import Dataset, DataLoader
from PIL import Image
root="E:/fashion_mnist/" def default_loader(path):
return Image.open(path).convert('RGB')
class MyDataset(Dataset):
def __init__(self, txt, transform=None, target_transform=None, loader=default_loader):
fh = open(txt, 'r')
imgs = []
for line in fh:
line = line.strip('\n')
line = line.rstrip()
words = line.split()
imgs.append((words[0],int(words[1])))
self.imgs = imgs
self.transform = transform
self.target_transform = target_transform
self.loader = loader def __getitem__(self, index):
fn, label = self.imgs[index]
img = self.loader(fn)
if self.transform is not None:
img = self.transform(img)
return img,label def __len__(self):
return len(self.imgs) train_data=MyDataset(txt=root+'train.txt', transform=transforms.ToTensor())
test_data=MyDataset(txt=root+'test.txt', transform=transforms.ToTensor())
train_loader = DataLoader(dataset=train_data, batch_size=64, shuffle=True)
test_loader = DataLoader(dataset=test_data, batch_size=64) #-----------------create the Net and training------------------------ class Net(torch.nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = torch.nn.Sequential(
torch.nn.Conv2d(3, 32, 3, 1, 1),
torch.nn.ReLU(),
torch.nn.MaxPool2d(2))
self.conv2 = torch.nn.Sequential(
torch.nn.Conv2d(32, 64, 3, 1, 1),
torch.nn.ReLU(),
torch.nn.MaxPool2d(2)
)
self.conv3 = torch.nn.Sequential(
torch.nn.Conv2d(64, 64, 3, 1, 1),
torch.nn.ReLU(),
torch.nn.MaxPool2d(2)
)
self.dense = torch.nn.Sequential(
torch.nn.Linear(64 * 3 * 3, 128),
torch.nn.ReLU(),
torch.nn.Linear(128, 10)
) def forward(self, x):
conv1_out = self.conv1(x)
conv2_out = self.conv2(conv1_out)
conv3_out = self.conv3(conv2_out)
res = conv3_out.view(conv3_out.size(0), -1)
out = self.dense(res)
return out model = Net()
print(model) optimizer = torch.optim.Adam(model.parameters())
loss_func = torch.nn.CrossEntropyLoss() for epoch in range(10):
print('epoch {}'.format(epoch + 1))
# training-----------------------------
train_loss = 0.
train_acc = 0.
for batch_x, batch_y in train_loader:
batch_x, batch_y = Variable(batch_x), Variable(batch_y)
out = model(batch_x)
loss = loss_func(out, batch_y)
train_loss += loss.data
pred = torch.max(out, 1)[1]
train_correct = (pred == batch_y).sum()
train_acc += train_correct.data
optimizer.zero_grad()
loss.backward()
optimizer.step()
print('Train Loss: {:.6f}, Acc: {:.6f}'.format(train_loss / (len(
train_data)), train_acc / (len(train_data)))) # evaluation--------------------------------
model.eval()
eval_loss = 0.
eval_acc = 0.
for batch_x, batch_y in test_loader:
batch_x, batch_y = Variable(batch_x, volatile=True), Variable(batch_y, volatile=True)
out = model(batch_x)
loss = loss_func(out, batch_y)
eval_loss += loss.data
pred = torch.max(out, 1)[1]
num_correct = (pred == batch_y).sum()
eval_acc += num_correct.data
print('Test Loss: {:.6f}, Acc: {:.6f}'.format(eval_loss / (len(
test_data)), eval_acc / (len(test_data))))
版本2修改的地方
原文：https://blog.csdn.net/shang_jia/article/details/82936074
原文：https://www.liangzl.com/get-article-detail-8524.html
注意：下面的代码不管，下面是第一次测试的时候，下载错了数据集
问题：这里的数据集是数字，不是这个数据集，代码里面是用的fashion-mnist这个数据集
1、下载mnist数据集
地址：http://yann.lecun.com/exdb/mnist/
下面这四个都要下载，下载完成后，解压到同一个目录，我是解压到“E:/fashion_mnist/”这个目录里面，好和下面的代码目录一致
解压完成后，需要修改一下文件名，如（修改原因：保持和下面代码一样，避免出现其它问题）：
修改前：t10k-images.idx3-ubyte
修改后：t10k-images-idx3-ubyte
我是第一次弄这玩意，所以尽量弄得白痴些，走弯路很烦，有时候一点点小问题就弄半天，其实就是别人有那么一点没讲清楚，然后就会搞很久
Python 10 训练模型的更多相关文章
- Python 10 —— 杂
Python 10 —— 杂 科学计算 NumPy:数组,数组函数,傅里叶变换 SciPy:依赖于NumPy,提供更多工具,比如绘图 绘图 Matplitlib:依赖于NumPy和Tkinter
- python 10大算法之一 LinearRegression 笔记
简单的线性回归预测房价 #!/usr/bin/env python # encoding: utf-8 """ @version: @author: --*--. @fi ...
- Python 10 协程，异步IO,Paramiko
本节内容 Gevent协程 异步IO Paramiko 携程 协程,又称为微线程,纤程(coroutine).是一种用户态的轻量级线程. 协程拥有自己的寄存器上下文和栈.协程调度切换时,将寄存器上下文 ...
- python 10分钟入门pandas
本文是对pandas官方网站上<10 Minutes to pandas>的一个简单的翻译,原文在这里.这篇文章是对pandas的一个简单的介绍,详细的介绍请参考:Cookbook .习惯 ...
- [ Python - 10 ] 练习：批量管理主机工具
需求: 主机分组 登录后显示主机分组,选择分组后查看主机列表 可批量执行命令.发送文件,结果实时返回 主机用户名密码可以不同 流程图: 说明: ## 需求: 主机分组 登录后显示主机分组,选择分组后查 ...
- python 10 动态参数
目录 1. 函数的动态参数 1.1 动态位置参数(*arges) 1.2 动态关键字参数 (**kwargs) 1.3 万能传参: 2. 函数的注释 3. 名称空间 4. 函数嵌套 5. 函数变量修改 ...
- [Advanced Python] 10 - Transfer parameters
动态库调用 一.Python调用 .so From: Python调用Linux下的动态库(.so) (1) 生成.so:.c to .so lolo@-id:workme$ gcc -Wall -g ...
- Python——10模块
*/ * Copyright (c) 2016,烟台大学计算机与控制工程学院 * All rights reserved. * 文件名:text.cpp * 作者:常轩 * 微信公众号:Worldhe ...
- python 10 else EasyGui(转载）
else语句 if else 要么怎么样,要么不怎么样 while else 干完了能怎样,干不完就不怎样 (异常处理) else 没有问题,就干吧 try: int('a') except Valu ...
随机推荐
- Lambda表达式和函数式编程
Lambda表达式和函数式编程 https://www.cnblogs.com/bigbigbigo/p/8422579.html https://www.runoob.com/java/java8- ...
- 开发dubbo应用程序(一)入门demo详解
1.简介: 引用自Dubbo官方文档简介: http://dubbo.apache.org/zh-cn/docs/user/dependencies.html 随着互联网的发展,网站应用的规模不断扩大 ...
- jQuery实现form表单基于ajax无刷新提交方法详解
本文实例讲述了jQuery实现form表单基于ajax无刷新提交方法.分享给大家供大家参考,具体如下: 首先,新建Login.html页面: <!DOCTYPE html PUBLIC &quo ...
- python基础03--int,bool,str
1.1 数字int 1.i = 100 i.bit_length() 转化为二进制的最小位数 1.2 布尔 bool 1.True False 0是False 1.3 数据转换 ...
- Netty入门系列(1) --使用Netty搭建服务端和客户端
引言 前面我们介绍了网络一些基本的概念,虽然说这些很难吧,但是至少要做到理解吧.有了之前的基础,我们来正式揭开Netty这神秘的面纱就会简单很多. 服务端 public class PrintServ ...
- xcode11新项目删除main.storyboard 两种方法
方法一 心急的童鞋按照老操作完成后再按照如下操作即可 /** 弃用storboard 1.info.plist去除 <key>UIApplicationSceneManifest</ ...
- underscore_1: map()
map()是underscore.js中一个处理数组和对象的方法. params: 1. array || obj 2. callback 3. content 上下文指向 使用: var obj = ...
- Django 连接 MySQL 数据库及常见报错解决
目录 Django 连接 MySQL数据库及常见报错解决 终端或者数据库管理工具连接 MySQL ,并新建项目所需数据库 安装访问 MySQL 的 Python 模块 Django 相关配置 可能会遇 ...
- powershell 远程下载并执行
远程下载文件到本地并执行cmd.exe /c powershell.exe -ExecutionPolicy bypass -noprofile -windowstyle hidden (new-ob ...
- android中如何实现UI的实时更新---需要考虑电量和流量
1.如果不考虑电量和流量的话,只需要在对应的activity里面继承Runnable,在run方法里面写一个while死循环,调用接口返回数据,如果数据发生了变化,就立即更新UI 2.需要考虑电量的话 ...