当前位置： 首页 > news >正文

K折交叉验证代码实现——详细注释版

news 2024/10/24 3:46:10

在这里插入图片描述

正常方法

#---------------------------------Torch Modules --------------------------------------------------------
from __future__ import print_function
import numpy as np
import pandas as pd
import torch.nn as nn
import math
import torch.nn.functional as F
import torch
import torchvision
from torch.nn import init
import torch.optim as optim
from torchvision import datasets, transforms
from torchvision import models
import torch.nn.functional as F
from torch.utils import data
import matplotlib.pyplot as plt
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"

###-----------------------------------variables-----------------------------------------------
# for Normalization
mean = [0.5]
std = [0.5]
# batch size
batch_size =128
epoch = 1        # epoch
lr = 0.01

##-----------------------------------Commands to download and perpare the MNIST dataset ------------------------------------
train_transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize(mean, std)])test_transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize(mean, std)])train_loader = torch.utils.data.DataLoader(datasets.MNIST('./mnist', train=True, download=True,transform=train_transform),batch_size=batch_size, shuffle=True) # train datasettest_loader = torch.utils.data.DataLoader(datasets.MNIST('./mnist', train=False, transform=test_transform),batch_size=batch_size, shuffle=False) # test dataset loader的形状为128,1,28,28

#visualization
def show_images(imgs, num_rows, num_cols, titles=None, scale=1.5): """Plot a list of images."""figsize = (num_cols * scale, num_rows * scale)_, axes = plt.subplots(num_rows, num_cols, figsize=figsize)axes = axes.flatten()for i, (ax, img) in enumerate(zip(axes, imgs)):if torch.is_tensor(img):# Tensor Imageax.imshow(img.numpy())else:# PIL Imageax.imshow(img)ax.axes.get_xaxis().set_visible(False)ax.axes.get_yaxis().set_visible(False)if titles:ax.set_title(titles[i])return axes
mnist_train = torchvision.datasets.MNIST(root="../data", train=True,#load minist
transform=train_transform,
download=True)
X, y = next(iter(data.DataLoader(mnist_train, batch_size=18)))
show_images(X.reshape(18, 28, 28), 2, 9)

在这里插入图片描述

model = nn.Sequential(nn.Flatten(), nn.Linear(784, 100), nn.ReLU(),nn.Linear(100, 10))#28*28，展平到784，最后被分类为10种,中间层的神经元数量自定义
def init_weights(m):#初始化权重if type(m) == nn.Linear:#如果只有一个线性层，设置std为0.01nn.init.normal_(m.weight, std=0.01)
model.apply(init_weights);## Loss function
criterion = torch.nn.CrossEntropyLoss() # pytorch's cross entropy loss function，多分类一般使用交叉熵# definin which paramters to train only the CNN model parameters
optimizer = torch.optim.SGD(model.parameters(),lr)#优化器，设置随机梯度下降

# defining the training function
# Train baseline classifier on clean data
def train(model, optimizer,criterion,epoch): model.train() # setting up for trainingfor batch_idx, (data, target) in enumerate(train_loader): # data contains the image and target contains the label = 0/1/2/3/4/5/6/7/8/9data = data.view(-1, 28*28).requires_grad_()#此处图像被展平了，bs是128，输入是28*28optimizer.zero_grad() # setting gradient to zerooutput = model(data) # forwardloss = criterion(output, target) # loss computationloss.backward() # back propagation here pytorch will take care of itoptimizer.step() # updating the weight valuesif batch_idx % 100 == 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()))

# to evaluate the model
## validation of test accuracy
def test(model, criterion, val_loader, epoch,train= False):    model.eval()test_loss = 0correct = 0  with torch.no_grad():for batch_idx, (data, target) in enumerate(val_loader):data = data.view(-1, 28*28).requires_grad_()output = model(data)test_loss += criterion(output, target).item() # sum up batch losspred = output.argmax(1, keepdim=True) # get the index of the max log-probabilitycorrect += pred.eq(target.view_as(pred)).sum().item() # if pred == target then correct +=1test_loss /= len(val_loader.dataset) # average test lossif train == False:print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.4f}%)\n'.format(test_loss, correct, val_loader.sampler.__len__(),100. * correct / val_loader.sampler.__len__() ))if train == True:print('\nTrain set: Average loss: {:.4f}, Accuracy: {}/{} ({:.4f}%)\n'.format(test_loss, correct, val_loader.sampler.__len__(),100. * correct / val_loader.sampler.__len__() ))return 100. * correct / val_loader.sampler.__len__() 

test_acc = torch.zeros([epoch])
train_acc = torch.zeros([epoch])
## training the logistic model
for i in range(epoch):train(model, optimizer,criterion,i)train_acc[i] = test(model, criterion, train_loader, i,train=True) #Testing the the current CNNtest_acc[i] = test(model, criterion, test_loader, i)if not os.path.exists('./saved_model'):os.makedirs('./saved_model')torch.save(model.state_dict(),'./saved_model/model_normal.bin')

Train Epoch: 0 [0/60000 (0%)] Loss: 0.314632
Train Epoch: 0 [12800/60000 (21%)] Loss: 0.283743
Train Epoch: 0 [25600/60000 (43%)] Loss: 0.229258
Train Epoch: 0 [38400/60000 (64%)] Loss: 0.219923
Train Epoch: 0 [51200/60000 (85%)] Loss: 0.187836
Train set: Average loss: 0.0020, Accuracy: 55673/60000 (92.7883%)
Test set: Average loss: 0.0020, Accuracy: 9284/10000 (92.8400%)

K折交叉验证

#!pip install sklearn -i https://pypi.mirrors.ustc.edu.cn/simple
from sklearn.model_selection import KFold
train_init = datasets.MNIST('./mnist', train=True,transform=train_transform)test_init =  datasets.MNIST('./mnist', train=False, transform=test_transform)# the dataset for k fold cross validation   
dataFold = torch.utils.data.ConcatDataset([train_init, test_init])#将验证集和测试集合并def train_flod_Mnist(k_split_value):different_k_mse = []kf = KFold(n_splits=k_split_value,shuffle=True, random_state=2024)  # init KFold 10折交叉for train_index , test_index in kf.split(dataFold):  # split  # get train, val train_fold = torch.utils.data.dataset.Subset(dataFold, train_index)test_fold = torch.utils.data.dataset.Subset(dataFold, test_index) # package type of DataLoadertrain_loader = torch.utils.data.DataLoader(dataset=train_fold, batch_size=batch_size, shuffle=True)test_loader = torch.utils.data.DataLoader(dataset=test_fold, batch_size=batch_size, shuffle=True)# train modeltest_acc = torch.zeros([epoch])#记录acctrain_acc = torch.zeros([epoch])## training the logistic modelfor i in range(epoch):train(model, optimizer,criterion,i)train_acc[i] = test(model, criterion, train_loader, i,train=True) #Testing the the current CNNtest_acc[i] = test(model, criterion, test_loader, i)#torch.save(model,'perceptron.pt')# one epoch, all accdifferent_k_mse.append(np.array(test_acc))return different_k_mse

testAcc_compare_map = {}
for k_split_value in range(10, 10+1): print('now k_split_value is:', k_split_value)testAcc_compare_map[k_split_value] = train_flod_Mnist(k_split_value)

now k_split_value is: 10
tensor([0.])
Train Epoch: 0 [0/60000 (0%)] Loss: 0.187658
Train Epoch: 0 [12800/60000 (21%)] Loss: 0.191175
Train Epoch: 0 [25600/60000 (43%)] Loss: 0.166395
Train Epoch: 0 [38400/60000 (64%)] Loss: 0.216365
Train Epoch: 0 [51200/60000 (85%)] Loss: 0.156119
Train set: Average loss: 0.0015, Accuracy: 59648/63000 (94.6794%)
Test set: Average loss: 0.0018, Accuracy: 6550/7000 (93.5714%)
tensor([0.])
Train Epoch: 0 [0/60000 (0%)] Loss: 0.220123
Train Epoch: 0 [12800/60000 (21%)] Loss: 0.135370
Train Epoch: 0 [25600/60000 (43%)] Loss: 0.132626
Train Epoch: 0 [38400/60000 (64%)] Loss: 0.258545
Train Epoch: 0 [51200/60000 (85%)] Loss: 0.181543
Train set: Average loss: 0.0015, Accuracy: 59698/63000 (94.7587%)
Test set: Average loss: 0.0015, Accuracy: 6622/7000 (94.6000%)
tensor([0.])
Train Epoch: 0 [0/60000 (0%)] Loss: 0.263651
Train Epoch: 0 [12800/60000 (21%)] Loss: 0.204342
Train Epoch: 0 [25600/60000 (43%)] Loss: 0.141438
Train Epoch: 0 [38400/60000 (64%)] Loss: 0.137843
Train Epoch: 0 [51200/60000 (85%)] Loss: 0.217006
Train set: Average loss: 0.0014, Accuracy: 59751/63000 (94.8429%)
Test set: Average loss: 0.0014, Accuracy: 6639/7000 (94.8429%)
tensor([0.])
Train Epoch: 0 [0/60000 (0%)] Loss: 0.166842
Train Epoch: 0 [12800/60000 (21%)] Loss: 0.096612
Train Epoch: 0 [25600/60000 (43%)] Loss: 0.230569
Train Epoch: 0 [38400/60000 (64%)] Loss: 0.109163
Train Epoch: 0 [51200/60000 (85%)] Loss: 0.101741
Train set: Average loss: 0.0014, Accuracy: 59757/63000 (94.8524%)
Test set: Average loss: 0.0013, Accuracy: 6669/7000 (95.2714%)
tensor([0.])
Train Epoch: 0 [0/60000 (0%)] Loss: 0.113768
Train Epoch: 0 [12800/60000 (21%)] Loss: 0.202454
Train Epoch: 0 [25600/60000 (43%)] Loss: 0.119112
Train Epoch: 0 [38400/60000 (64%)] Loss: 0.116779
Train Epoch: 0 [51200/60000 (85%)] Loss: 0.376868
Train set: Average loss: 0.0014, Accuracy: 59879/63000 (95.0460%)
Test set: Average loss: 0.0013, Accuracy: 6682/7000 (95.4571%)
tensor([0.])
Train Epoch: 0 [0/60000 (0%)] Loss: 0.100557
Train Epoch: 0 [12800/60000 (21%)] Loss: 0.189366
Train Epoch: 0 [25600/60000 (43%)] Loss: 0.174508
Train Epoch: 0 [38400/60000 (64%)] Loss: 0.104910
Train Epoch: 0 [51200/60000 (85%)] Loss: 0.146227
Train set: Average loss: 0.0013, Accuracy: 59914/63000 (95.1016%)
Test set: Average loss: 0.0013, Accuracy: 6652/7000 (95.0286%)
tensor([0.])
Train Epoch: 0 [0/60000 (0%)] Loss: 0.103640
Train Epoch: 0 [12800/60000 (21%)] Loss: 0.179051
Train Epoch: 0 [25600/60000 (43%)] Loss: 0.138919
Train Epoch: 0 [38400/60000 (64%)] Loss: 0.214437
Train Epoch: 0 [51200/60000 (85%)] Loss: 0.127463
Train set: Average loss: 0.0013, Accuracy: 59986/63000 (95.2159%)
Test set: Average loss: 0.0013, Accuracy: 6674/7000 (95.3429%)
tensor([0.])
Train Epoch: 0 [0/60000 (0%)] Loss: 0.154551
Train Epoch: 0 [12800/60000 (21%)] Loss: 0.157627
Train Epoch: 0 [25600/60000 (43%)] Loss: 0.163700
Train Epoch: 0 [38400/60000 (64%)] Loss: 0.148417
Train Epoch: 0 [51200/60000 (85%)] Loss: 0.130215
Train set: Average loss: 0.0013, Accuracy: 60056/63000 (95.3270%)
Test set: Average loss: 0.0013, Accuracy: 6685/7000 (95.5000%)
tensor([0.])
Train Epoch: 0 [0/60000 (0%)] Loss: 0.146108
Train Epoch: 0 [12800/60000 (21%)] Loss: 0.205999
Train Epoch: 0 [25600/60000 (43%)] Loss: 0.115849
Train Epoch: 0 [38400/60000 (64%)] Loss: 0.222786
Train Epoch: 0 [51200/60000 (85%)] Loss: 0.178309
Train set: Average loss: 0.0012, Accuracy: 60162/63000 (95.4952%)
Test set: Average loss: 0.0013, Accuracy: 6683/7000 (95.4714%)
tensor([0.])
Train Epoch: 0 [0/60000 (0%)] Loss: 0.240678
Train Epoch: 0 [12800/60000 (21%)] Loss: 0.234599
Train Epoch: 0 [25600/60000 (43%)] Loss: 0.183265
Train Epoch: 0 [38400/60000 (64%)] Loss: 0.148125
Train Epoch: 0 [51200/60000 (85%)] Loss: 0.168119
Train set: Average loss: 0.0012, Accuracy: 60174/63000 (95.5143%)
Test set: Average loss: 0.0012, Accuracy: 6716/7000 (95.9429%)


http://www.mrgr.cn/news/57303.html

相关文章：

  • RocketMQ | 源码分析 | Broker控制器的启动
  • 算法的学习笔记—丑数(牛客JZ49)
  • Python 第六节 变化的文字
  • AutoSar AP CM实例说明符的使用方法总结
  • Python面向对象编程
  • Flutter鸿蒙next 布局架构原理详解
  • IPC 信号-Signal Linux环境
  • 栈的顺序存储总览
  • 关于风险系统解读最全最专业文章：一篇文章讲透风险，跨学科搞懂风险游戏规则，风险信任风险主观性客观性风险本质人格特质与风险态度技术风险系统风险社会新产品风险
  • 栈和队列代码
  • ARM/Linux嵌入式面经（五二）：华为
  • Spring 设计模式之单例模式
  • C++新基础类型(C++11~C++20)
  • ECharts图表图例11
  • 解决cad找不到vcruntime140_1.dll,无法继续执行代码的6种方法
  • 《YOLO 目标检测》—— YOLO v3 详细介绍
  • 拟态UI3.0个人页
  • django模板相关配置
  • 一个将.Geojson文件转成shapefile和kml文件的在线页面工具（续）
  • hive数据库,表操作
  • 前缀和 有图文 超详细整理通俗易懂
  • OpenEular + KVM + virt-manager 笔记
  • Python小程序 - 替换文件内容
  • 论文精读：TiC-CLIP: Continual Training of CLIP Models（三）
  • pdf表格读取和筛选
  • ArrayList 源码分析