一起深度学习——CIFAR10

本文主要是介绍一起深度学习——CIFAR10，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！

目的：

实现从数据集中进行分类，一共有10个类别。

实现步骤：

1、导包：

import collectionsimport torch
from torch import nn
from d2l import torch as d2l
import shutil
import os
import math
import pandas as pd
import torchvision

2、下载数据集

#下载数据集
d2l.DATA_HUB['cifar10_tiny'] = (d2l.DATA_URL + 'kaggle_cifar10_tiny.zip','2068874e4b9a9f0fb07ebe0ad2b29754449ccacd')# 如果使用完整的Kaggle竞赛的数据集，设置demo为False
demo = Trueif demo:data_dir = d2l.download_extract('cifar10_tiny')
else:data_dir = '../data/kaggle/cifar-10/'

3、整理数据集

ef read_csv_labels (fname):with open(fname,'r') as f:lines = f.readlines()[1:] #[1：0]表示从第二行开始读取，因为第一行是行头# 按照逗号分割每一行， 且rstrip 去除每行末尾的换行符# eg: ["apple,orange,banana\n"] => [['apple','orange','banana']]tokens = [l.rstrip().split(',') for l in lines]return dict((name,label) for name, label in tokens)labels = read_csv_labels(os.path.join(data_dir,'trainLabels.csv'))

4、将验证集从原始的训练集中拆分出来

def copyfile(filename,target_dir):os.makedirs(target_dir,exist_ok=True)shutil.copy(filename,target_dir)# print("训练样本：",len(labels))
# print("类别：",len(set(labels.values())))
def reorg_train_valid(data_dir,labels,valid_ratio):# Counter ：用于计算每个类别出现的次数# most_common() ：用于统计返回出现次数最多的元素（类别，次数），是一个列表，并且按照次数降序的方式存储# 【-1】表示取出列表中的最后一个元组。# 【1】 表示取出该元组的次数。n = collections.Counter(labels.values()).most_common()[-1][1]# math.floor(): 向下取整  math.ceil(): 向上取整# 每个类别分配给验证集的最小个数n_valid_per_label = max(1,math.floor((n * valid_ratio)))label_count = {}for photo in os.listdir(os.path.join(data_dir,'train')):label = labels[photo.split('.')[0]] #取出该标签所对应的类别# print(train_file)fname = os.path.join(data_dir,'train',photo)copyfile(fname,os.path.join(data_dir,'train_valid_test','train_valid',label))#如果该类别没有在label_count中或者是 数量小于规定的最小值，则将其复制到验证集中if label not in label_count or label_count[label] < n_valid_per_label:copyfile(fname,os.path.join(data_dir,'train_valid_test','valid',label))label_count[label] = label_count.get(label,0) +1else:copyfile(fname,os.path.join(data_dir,'train_valid_test','train',label))return n_valid_per_labeldef reorg_test(data_dir):for test_file in os.listdir(os.path.join(data_dir,'test')):copyfile(os.path.join(data_dir,'test',test_file), os.path.join(data_dir,'train_valid_test','test','unknown'))def reorg_cifar10_data(data_dir,valid_ratio):labels = read_csv_labels(os.path.join(data_dir,'trainLabels.csv'))reorg_train_valid(data_dir,labels,valid_ratio)reorg_test(data_dir)batch_size = 32 if demo else 128
valid_ratio = 0.1
reorg_cifar10_data(data_dir,valid_ratio)
"""
结果会生成一个train_valid_test的文件夹，里面有：
- test文件夹---unknow文件夹：5张没有标签的测试照片
- train_valid文件夹---10个类被的文件夹：每个文件夹包含所属类别的全部照片
- train文件夹--10个类别的文件夹：每个文件夹下包含90%的照片用于训练
- valid文件夹--10个类别的文件夹：每个文件夹下包含10%的照片用于验证
"""

5、数据增强

transform_train = torchvision.transforms.Compose([# 原本图像是32*32，先放大成40*40， 在随机裁剪为32*32，实现训练数据的增强torchvision.transforms.Resize(40),torchvision.transforms.RandomResizedCrop(32, scale=(0.64, 1.0), ratio=(1.0, 1.0)),torchvision.transforms.RandomHorizontalFlip(),torchvision.transforms.ToTensor(),torchvision.transforms.Normalize([0.4914, 0.4822, 0.4465],[0.2023, 0.1994, 0.2010])
])
transform_test = torchvision.transforms.Compose([torchvision.transforms.ToTensor(),# 标准化图像的每个通道 ： 消除评估结果中的随机性torchvision.transforms.Normalize([0.4914, 0.4822, 0.4465],[0.2023, 0.1994, 0.2010])
])

6、加载数据集

#加载数据集
train_ds,train_valid_ds = [torchvision.datasets.ImageFolder(os.path.join(data_dir,'train_valid_test',folder),transform=transform_train)for folder in ['train','train_valid']
]
valid_ds, test_ds = [torchvision.datasets.ImageFolder(os.path.join(data_dir, 'train_valid_test', folder), transform=transform_test) for folder in ['valid', 'test']
]
#定义迭代器
train_iter, train_valid_iter = [torch.utils.data.DataLoader(dataset, batch_size, shuffle=True, drop_last=True) for dataset in (train_ds, train_valid_ds)
]valid_iter = torch.utils.data.DataLoader(valid_ds,batch_size,shuffle=False,drop_last=True
)
test_iter = torch.utils.data.DataLoader(test_ds,batch_size,shuffle=False,drop_last=False
)

7、定义训练模型：

def get_net():num_classes = 10 #输出标签net = d2l.resnet18(num_classes,in_channels=3)return net

损失函数：

#损失函数
loss = nn.CrossEntropyLoss(reduction='none')

8、定义训练函数：

#定义训练函数
def train(net,train_iter,valid_iter,num_epochs,lr,wd,devices,lr_period,lr_decay):trainer = torch.optim.SGD(net.parameters(),lr=lr,momentum=0.9,weight_decay=wd)#学习率调度器：在经过lr_period个epoch之后，将学习率乘以lr_decay.scheduler = torch.optim.lr_scheduler.StepLR(trainer,lr_period,lr_decay)num_batches,timer = len(train_iter),d2l.Timer()legend = ['train_loss','train_acc']if valid_iter is not None:legend.append('valid_acc')animator = d2l.Animator(xlabel='epoch',xlim=[1,num_epochs],legend=legend)net = nn.DataParallel(net,device_ids=devices).to(devices[0])for epoch in range(num_epochs):# 设置为训练模式net.train()metric = d2l.Accumulator(3)for i,(X,y) in enumerate(train_iter):timer.start()l,acc = d2l.train_batch_ch13(net,X,y,loss,trainer,devices)metric.add(l,acc,y.shape[0])timer.stop()if (i + 1) % (num_batches // 5 ) ==0 or i == num_batches - 1:animator.add(epoch + (i + 1)/num_batches,(metric[0]/metric[2],metric[1]/metric[2],None))if valid_iter is not None:valid_acc = d2l.evaluate_accuracy_gpu(net,valid_iter)animator.add(epoch+1,(None,None,valid_acc))scheduler.step()  #更新学习率measures = (f'train loss {metric[0] / metric[2]:.3f},'f'train acc{metric[1] / metric[2]:.3f}')if valid_iter is not None:measures += f', valid acc {valid_acc:.3f}'print(measures + f'\n{metric[2] * num_epochs / timer.sum():.1f}'f'example/sec on {str(devices)}')

9、定义参数，开始训练：

import time# 在开头设置开始时间
start = time.perf_counter()  # start = time.clock() python3.8之前可以# 训练和验证模型
devices, num_epochs, lr, wd = d2l.try_all_gpus(), 100, 2e-4, 5e-4
lr_period, lr_decay, net = 4, 0.9, get_net()
train(net, train_iter, valid_iter, num_epochs, lr, wd, devices, lr_period, lr_decay)# 在程序运行结束的位置添加结束时间
end = time.perf_counter()  # end = time.clock()  python3.8之前可以# 再将其进行打印，即可显示出程序完成的运行耗时
print(f'运行耗时{(end-start):.4f}')

这篇关于一起深度学习——CIFAR10的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！

---