seo网站诊断优化流程,wamp网站根目录配置,net网站开发视频,网站投资设计#x1f525;博客主页#xff1a; A_SHOWY#x1f3a5;系列专栏#xff1a;力扣刷题总结录 数据结构 云计算 数字图像处理 力扣每日一题_ 1.安装pytorch以及anaconda配置 尽量保持默认的通道#xff0c;每次写指令把镜像地址写上就行。 defaults优先级是最低的#… 博客主页 A_SHOWY系列专栏力扣刷题总结录 数据结构  云计算  数字图像处理  力扣每日一题_  1.安装pytorch以及anaconda配置 尽量保持默认的通道每次写指令把镜像地址写上就行。 defaults优先级是最低的如果添加了新的通道会先去新添加的里面找有没有想要的包没有的话就去defaults里再找。 PyCharm添加Anaconda中的虚拟环境Python解释器出现Conda executable is not found PyCharm添加Anaconda中的虚拟环境Python解释器出现Conda executable is not found-CSDN博客https://blog.csdn.net/s1hjf/article/details/128759758?ops_request_misc%7B%22request%5Fid%22%3A%22167612835216800213082077%22%2C%22scm%22%3A%2220140713.130102334..%22%7Drequest_id167612835216800213082077biz_id0utm_mediumdistribute.pc_search_result.none-task-blog-2~all~baidu_landing_v2~default-2-128759758-null-null.142^v73^pc_search_v2,201^v4^add_ask,239^v1^insert_chatgptutm_termconda excutable is not foundspm1018.2226.3001.4187 这个终端设置以后点击可以出来anaconda的命令行 下载新的项目的时候在pycharm里打开项目然后点击文件-设置-项目-python解释器-添加解释器 有的项目里会有requirements文件点进去会非常智能的弹出来install requirements然后就把所有需要的包装上了。 直接运行项目看哪个包不存在报错然后打开anaconda命令行先activate然后再conda install 包名有时候不行可能因为包名不是这个就把conda install 包名复制到必应搜索是什么复制过去安装就行。有时候conda install找不到但是pip install能找到。 还有一种方法打开项目文件然后找到路径复制进命令行窗口前面输入一个cd/d cd不能跨盘使用然后再输入下面的pip install -r requirements.txt 就会把所有需要的包都安装上 help函数看到官方的解释文档 2.pytorch加载数据 Dataset提供一种方式去获取数据及其label Dataloader为后面的网络提供不同的数据形式 3.Tensorboard的使用 tensorboard --logdirlogs --port6007要是想打开网页就不能ctrlc停止终端要一直运行着 在tensorboard显示需要tensor图片类型 这里要指定文件夹不然会自动出来runs文件夹这样的话要写--logdirruns事件文件所在文件夹名称才可以。 #Tendorboard 自定义端口 4.Transform的使用 transform的结构和用法 # chen # 2024/3/10 17:10 from PIL import Image from torchvision import transforms#python的用法——》tensor数据类型 #transforms两个左行 #1.transforms如何使用 #2.为什么需要tensor 的数据类型 img_path F:\\pythonLearn\\pythonProject\\hymenoptera_data\\train\\ants\\7759525_1363d24e88.jpg img Image.open(img_path) print(img)#PIL.JpegImagePlugin.JpegImageFile image modeRGB size500x333 at 0x24347D59F60 #1怎么用 tensor_1 transforms.ToTensor() tensor_img tensor_1(img) print(tensor_img) #2.为什么用 # 包装了一些反向神经网络一些理论的参数 image_pathdataset/train/ants_image/0013035.jpg imgImage.open(image_path) tensor_transtransforms.ToTensor() # 创建了一个实例并把实例赋值给了tensor_trans tensor_imgtensor_trans(img) # 一个类定义了 __call__ 方法那么该类的实例可以像函数一样被调用就不用用.来调用了 应用到tensorboard  #应用到tensorboard import numpy as np from PIL import Image from torch.utils.tensorboard import SummaryWriter from torchvision import transforms writer SummaryWriter(logs) image_path hymenoptera_data/train/ants/0013035.jpg img_PIL Image.open(image_path) tensor_1 transforms.ToTensor() tensor_img tensor_1(img_PIL) writer.add_image(test,tensor_img) 常见的transform Call的用法 不用加点调用函数就是方便 # chen # 2024/3/11 15:55 class Person:def __call__(self, name):print(__call__ hello name)def sayhello(self,name):print(hello name)person Person() person(zhangsan) person.sayhello(lisi) Normalize方法 主要是关注输入输出类型多看官方文档 关注方法需要什么参数有等于号的就是默认的可以不写的参数 输出不知道的时候可以直接printimg或者printtypeimg就会出来数据类型 # chen # 2024/3/8 1:10import numpy as np from PIL import Image from torch.utils.tensorboard import SummaryWriter from torchvision import transforms writer SummaryWriter(logs) image_path hymenoptera_data/train/ants/0013035.jpg img_PIL Image.open(image_path) #tosonser的使用 tensor_1 transforms.ToTensor() tensor_img tensor_1(img_PIL) writer.add_image(test,tensor_img) writer.close() #normalize方法 print(tensor_img[0][0][0]) trans_norm transforms.Normalize([0.5,0.5,0.5],[0.5,0.5,0.5]) img_norm trans_norm(tensor_img) print(img_norm[0][0][0]) writer.add_image(Normalize,img_norm) writer.close() resize的使用 #resize方法 print(img_PIL.size) trans_resize transforms.Resize((512,512)) img_resize trans_resize(img_PIL) #转成tonser去tensorboard看 img_resize tensor_1(img_resize) print(img_PIL.size) writer.add_image(Resize,img_resize) writer.close() resize2-compose的使用 #compose___Resize2 trans_resize_2 transforms.Resize(512) trans_comp transforms.Compose([trans_resize_2,tensor_1])#一个是刚创建的对象一个是tosensor的对象后一个的输入和前一个的输出一定匹配 img_com trans_comp(img_PIL) writer.add_image(Compose,img_com,0) writer.close() 随机裁剪 #randomCrop随机裁剪 trans_random transforms.RandomCrop(512) trans_comp_2 transforms.Compose([trans_random,tensor_1])#先随机裁剪再转为tensor for i in range(10):img_crop trans_comp_2(img_PIL)writer.add_image(randomCrop,img_crop,i) writer.close() 5.Torchvision中数据集的使用 可以按住ctrl放在CIFAR10上面 然后去原始文件里找下载路径放到迅雷里下载download一直设置为True就行。下载好了把压缩包复制到自己创建的文件夹下这个文件夹要和代码里写的名字一样运行python会自动解压校验。 # chen # 2024/3/12 11:32 import torchvision from torch.utils.tensorboard import SummaryWriterdataset_tran torchvision.transforms.Compose([torchvision.transforms.ToTensor(),torchvision.transforms.Resize(512)])train_set torchvision.datasets.CIFAR10(root ./dataset,train True,transformdataset_tran,downloadTrue) test_set torchvision.datasets.CIFAR10(root./dataset,train False,transformdataset_tran,downloadTrue) print(test_set[0])writer SummaryWriter(p10) for i in range(10):img,target test_set[i]writer.add_image(test_set,img,i) writer.close() 6.Dataloader的使用 Dataset像一摞扑克牌dataloader就是一次取出一组扑克牌 test_loaderDataLoader(datasettest_data,batch_size64,shuffleTrue,num_workers0,drop_lastFalse) batch_size就是一次取出多少张图片shuffle就是每次要不要打乱顺序drop就是要不要舍弃余数。 imgs和targets都是被打包的。 import torchvision.datasets from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWritertest_data torchvision.datasets.CIFAR10(root ./dataset,train False,transformtorchvision.transforms.ToTensor(),downloadTrue) test_loader DataLoader(datasettest_data,batch_size64,shuffleTrue,num_workers0,drop_lastTrue)#在数据集中每次取四个打乱数据集打包 #测试数据集中第一张图片及target img,target test_data[0] # print(img.shape) # print(target) writer SummaryWriter(dataloader)for epoch in range(2):step 0for data in test_loader:imgs,targets data# print(imgs.shape)# print(targets)writer.add_images(epoch2:{}.format(epoch),imgs,step)step step 1 writer.close() 每次取的四张图片3通道32×32的图片对target在进行打包 7.神经网络的基本骨架-nn.Module的使用 Neural-network 卷积操作 import torch.nn.functional as Foutput3F.conv2d(input,kernel,stride1,padding1)这个kernel是卷积核stride是卷积核每次移动的步数padding是是否对input进行填充padding1就是对input上下左右都填充一行默认填充值是0import torch import torch.nn.functional as F input torch.tensor([[1,2,0,3,1],[0,1,2,3,1],[1,2,1,0,0],[5,2,3,1,1],[2,1,0,1,1]]) kernel torch.tensor([[1,2,1],[0,1,0],[2,1,0]]) #torch类型是shape的转换 input torch.reshape(input,(1,1,5,5))#一个图像所以batch是1二维矩阵通道数也是1 kernel torch.reshape(kernel,(1,1,3,3)) print(input.shape) print(kernel.shape)output F.conv2d(input,kernel,stride1) print(output) 8.卷积层 两个卷积核-两个输出通道 6个channel不会显示了 import torchvision import torch from torch import nn from  torch.nn import Conv2d from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriterdataset torchvision.datasets.CIFAR10(..\data,train False,transformtorchvision.transforms.ToTensor(),downloadTrue) dataloader DataLoader(dataset,batch_size64)class Guozi(nn.Module):def __init__(self):super(Guozi,self).__init__()self.conv1 Conv2d(in_channels3,out_channels6,kernel_size3,stride1,padding0)def forward(self,x):x self.conv1(x)return x guozi Guozi() writer SummaryWriter(logs)step 0 for data in dataloader:imgs,target dataoutput guozi(imgs)print(imgs.shape)print(output.shape)writer.add_images(input,imgs,step)output torch.reshape(output,(-1,3,30,30))#6个channel不会显示了,转换一下writer.add_images(output,output,step)step step 1 writer.close() 9.最大池化的使用 Ceil_model是True就保留不足九个的那块的最大值默认是False的 相当于把参数数量变小了但是还保留特征 import torch import torchvision.datasets from torch import nn from torch.nn import MaxPool2d from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriterdataset torchvision.datasets.CIFAR10(chihua,train False,transformtorchvision.transforms.ToTensor(),downloadTrue) dataloader DataLoader(dataset,batch_size64)class Guozi(nn.Module):def __init__(self):super(Guozi,self).__init__()self.maxPool1 MaxPool2d(kernel_size3,ceil_modeFalse)def forward(self,input):output self.maxPool1(input)return outputguozi2 Guozi() writer SummaryWriter(logs2) step 0 for data in dataloader:imgs,targets datawriter.add_images(input,imgs,step)output guozi2(imgs)writer.add_images(output,output,step)step  step 1 writer.close() 10.非线性激活(提高泛化能力) 常用Sigmoid雅俗灰度范围Relu输出图像灰度大于0 的部分 建议第二种防止数据丢失默认就是false 11.tensor数据类型 张量 学numpy 12.线性层及其它层介绍 self.linear1Linear(in_features196608,out_features10)  #这是一个vgg16model # outputtorch.reshape(imgs,(1,1,1,-1))  #这个-1是让他根据前面设置的参数自动计算 # 也可以用torch.flatten outputtorch.flatten(imgs) class Guozi(nn.Module):def __init__(self):super(Guozi,self).__init__()self.linear1 Linear(196608,10)def forward(self,input):output self.linear1(input)return outputguozi Guozi()for data in dataloader:imgs,target dataprint(imgs.shape)#想变成1* 1 *1 *  %的形式output torch.reshape(imgs,(1,1,1,-1))print(output.shape)output guozi(output)print(output.shape) # output torch.reshape(imgs,(1,1,1,-1))output torch.flatten(imgs)#flatten把输入的数据展成一行 13.sequential的使用和搭建小实战 import torch from torch import nn from torch.nn import MaxPool2d, Flatten, Linear,Conv2dclass Guozi(nn.Module):def __init__(self):super(Guozi,self).__init__()self.conv1 Conv2d(3,32,5,padding 2)self.maxpool MaxPool2d(2)self.conv2 Conv2d(32,32,5,padding2)self.maxpool2 MaxPool2d(2)#这里有一个公式如果尺寸不变padding f -1/2f是kernelself.conv3 Conv2d(32,64,5,padding2)self.maxpool3 MaxPool2d(2)self.flatten Flatten()self.Liner1 Linear(1024,64)self.Liner2 Linear(64,10)def forward(self,x):x self.conv1(x)x self.maxpool(x)x self.conv2(x)x self.maxpool2(x)x self.conv3(x)x self.maxpool3(x)x self.flatten(x)x self.Liner1(x)x self.Liner2(x)return xguozi Guozi() print(guozi) #检验网络结构 input torch.ones((64,3,32,32)) output guozi(input) print(output.shape) 画的那是两个线性层 用sequential可以简化 class Guozi(nn.Module):def __init__(self):super(Guozi,self).__init__()# self.conv1 Conv2d(3,32,5,padding 2)# self.maxpool MaxPool2d(2)# self.conv2 Conv2d(32,32,5,padding2)# self.maxpool2 MaxPool2d(2)# #这里有一个公式如果尺寸不变padding f -1/2f是kernel# self.conv3 Conv2d(32,64,5,padding2)# self.maxpool3 MaxPool2d(2)# self.flatten Flatten()# self.Liner1 Linear(1024,64)# self.Liner2 Linear(64,10)self.model1 Sequential(Conv2d(3, 32, 5, padding2),MaxPool2d(2),Conv2d(32, 32, 5, padding2),MaxPool2d(2),Conv2d(32, 64, 5, padding2),MaxPool2d(2),Flatten(),Linear(1024, 64),Linear(64, 10))def forward(self,x):# x self.conv1(x)# x self.maxpool(x)# x self.conv2(x)# x self.maxpool2(x)# x self.conv3(x)# x self.maxpool3(x)# x self.flatten(x)# x self.Liner1(x)# x self.Liner2(x)x self.model1(x)return x#用tensorboard可视化一下writer SummaryWriter(logs_seq) writer.add_graph(guozi,input) writer.close() 14.损失函数与反向传播 import torch from torch.nn import L1Lossinputs torch.tensor([1,2,3],dtypetorch.float32) targets torch.tensor([1,2,5],dtypetorch.float32)loss L1Loss() result loss(inputs,targets) print(result) loss L1Loss(reductionsum)result loss(inputs,targets)print(result) 反向传播以后会出来每个参数对应的梯度grad #反向传播交叉熵import torch import torchvision.datasets from torch import nn from torch.nn import MaxPool2d, Flatten, Linear, Conv2d, Sequential from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriter dataset torchvision.datasets.CIFAR10(../data,train False,transformtorchvision.transforms.ToTensor(),download True) dataloader DataLoader(dataset,batch_size1) class Guozi(nn.Module):def __init__(self):super(Guozi,self).__init__()self.model1 Sequential(Conv2d(3, 32, 5, padding2),MaxPool2d(2),Conv2d(32, 32, 5, padding2),MaxPool2d(2),Conv2d(32, 64, 5, padding2),MaxPool2d(2),Flatten(),Linear(1024, 64),Linear(64, 10))def forward(self,x):x self.model1(x)return x loss nn.CrossEntropyLoss()#交叉熵 guozi Guozi() for data in dataloader:imgs,targets dataoutputs guozi(imgs)result_loss loss(outputs,targets)print(result_loss)#反向传播result_loss.backward() 15.优化器torch.OPTIM import torch import torchvision.datasets from torch import nn from torch.nn import MaxPool2d, Flatten, Linear, Conv2d, Sequential from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriter dataset torchvision.datasets.CIFAR10(../data,train False,transformtorchvision.transforms.ToTensor(),download True) dataloader DataLoader(dataset,batch_size1) class Guozi(nn.Module):def __init__(self):super(Guozi,self).__init__()self.model1 Sequential(Conv2d(3, 32, 5, padding2),MaxPool2d(2),Conv2d(32, 32, 5, padding2),MaxPool2d(2),Conv2d(32, 64, 5, padding2),MaxPool2d(2),Flatten(),Linear(1024, 64),Linear(64, 10))def forward(self,x):x self.model1(x)return x loss nn.CrossEntropyLoss()#交叉熵 guozi Guozi() optim torch.optim.SGD(guozi.parameters(),lr 0.01)#选择优化器然后传入参数 for epoch in range(20):running_loss 0.0for data in dataloader:imgs,targets dataoutputs guozi(imgs)result_loss loss(outputs,targets)#反向传播optim.zero_grad() # 把上一次的梯度清零result_loss.backward()#得到了每个参数调节的梯度必不可少optim.step() # 对每个参数进行调优running_loss result_loss# running_loss是每一轮训练的误差求和print(running_loss) 16.现有网络模型的使用及修改 import torchvision.datasets # # train_data torchvision.datasets.ImageNet(../data_image_net,split train,downloadTrue #                                            ,transformtorchvision.transforms.ToTensor()) vgg16_false torchvision.models.vgg16(pretrainedFalse)#仅仅加载网络模型,相当于只写了网络架构没有训练的参数参数随机 vgg16_true torchvision.models.vgg16(pretrainedTrue)#下载参数数据集上训练好的参数 print(vgg16_true)***import torchvision.datasets from torch import nn# # train_data torchvision.datasets.ImageNet(../data_image_net,split train,downloadTrue #                                            ,transformtorchvision.transforms.ToTensor()) vgg16_false torchvision.models.vgg16(pretrainedFalse)#仅仅加载网络模型,相当于只写了网络架构没有训练的参数参数随机 vgg16_true torchvision.models.vgg16(pretrainedTrue)#下载参数数据集上训练好的参数 print(vgg16_true) train_data torchvision.datasets.CIFAR10(../data,transformtorchvision.transforms.ToTensor(),train True,downloadTrue) #在最后加新的一层 vgg16_true.add_module(add_linear,nn.Linear(1000,10)) #直接在classifier加 vgg16_true.classifier.add_module(add_linear,nn.Linear(1000,10)) print(vgg16_true) # 直接改某一层 print(vgg16_false) vgg16_false.classifier[6] nn.Linear(4096,10) print((vgg16_false)) 17.模型的保存与读取 #保存方式1,不仅保存了网络模型结构还保存了模型参数 torch.save(vgg16,vgg16_method1.pth) #保存方式2推荐加载模型结构参数也都加载进来了 torch.save(vgg16.state_dict(),vgg16_method2.pth)#读取#方式1 model torch.load(vgg16_method1.pth) print(model)#方式2 #重新建立网络模型结构 vgg16 torchvision.models.vgg16(pretrainedFalse) vgg16.load_state_dict(torch.load(vgg16_method2.pth)) # model torch.load(vgg16_method2.pth) print(model) 陷阱如果用方式1加载自己建立的模型的话需要把模型定义复制过来或者是import定义模型的文件 *。但是不需要这一步了guozi Guozi( ) 18.完整的模型训练套路以CIFAR10为例 放在train和model文件下面了 # chen,model # 2024/3/18 0:40 #搭建神经网络 import torch from torch import nnclass Chenzi(nn.Module):def __init__(self):super(Chenzi,self).__init__()self.model nn.Sequential(nn.Conv2d(3,32,5,1,2),nn.MaxPool2d(2),nn.Conv2d(32,32,5,1,2),nn.MaxPool2d(2),nn.Conv2d(32,64,5,1,2),nn.MaxPool2d(2),nn.Flatten(),nn.Linear(64*4*4,64),nn.Linear(64,10))def forward(self,x):x self.model(x)return xif __name__ __main__:chenzi Chenzi()input torch.ones((64,3,32,32))output chenzi(input)print(output.shape) #输出torch.Size([64, 10])意思是输入了64个图片返回64行数据代表每一个图片在10个类中概率 # chen,train # chen # 2024/3/18 0:25 #准备数据集 import torch.optim.optimizer import torchvision from torch import nn from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriterfrom shizhan.model import Chenzi #准备数据集 train_data torchvision.datasets.CIFAR10(root ../data,trainTrue,transformtorchvision.transforms.ToTensor(),downloadTrue) test_data torchvision.datasets.CIFAR10(root ../data,trainFalse,transformtorchvision.transforms.ToTensor(),downloadTrue) #获得数据集长度 train_data_size len(train_data) test_data_size len(test_data) print(训练数据集的长度为{}.format(train_data_size)) print(测试数据集的长度为{}.format(test_data_size))#利用dataloader加载数据集train_dataloader DataLoader(train_data,64) test_dataloader  DataLoader(test_data,64)#创建网络模型 chenzi Chenzi() #损失函数 loss_fn nn.CrossEntropyLoss()#优化器 learning_rate 0.01 optimizer torch.optim.SGD(chenzi.parameters(),lr learning_rate)#设置训练网络一些参数 #记录训练次数测试数目和训练轮数 total_train_step 0 total_test_step 0 epoch 10#添加tensorboard writer SummaryWriter(../logs_train) #多次训练 chenzi.train() for i in range(epoch):# 训练步骤开始print(--------第{}论训练开始---------.format(i1))for data in train_dataloader:imgs,target dataoutputs chenzi(imgs)loss loss_fn(outputs,target)#先清零,优化器优化模型optimizer.zero_grad()loss.backward()optimizer.step()total_train_step 1if total_train_step % 100 0:#每逢100输出print(训练次数{}Loss{}.format(total_train_step,loss.item()))writer.add_scalar(train_loss,loss.item(),total_train_step) #测试步骤开始chenzi.eval()total_test_loss 0total_accuracy 0with torch.no_grad():#没有梯度for data in test_dataloader:imgs,targets dataoutputs chenzi(imgs)loss loss_fn(outputs,targets)total_test_loss loss.item()#正确率accuracy (outputs.argmax(1) targets).sum()total_accuracy accuracyprint(整体测试集的loss{}.format(total_test_loss))print(整体测试集的正确率{}.format(total_accuracy/test_data_size))writer.add_scalar(test_loss,total_test_loss,total_test_step)writer.add_scalar(test_accuracy,total_accuracy/test_data_size,total_test_step)total_test_step 1#保存每一轮训练的模型torch.save(chenzi,chenzi_{}.pth.format(i))print(模型已保存)writer.close() 补充检验分类问题的正确性 比如2分类问题input×2得到output[0.1,0.2][0.3,0.4]需要区分的是类别0和类别1通过函数argmax可以把output转换成preds[1][1]input targets[0][1]然后让predsinput targets就会得到[false,true]然后[false,true].sum()1 1是横着看0是竖着看 这两点不是必要的有的人的代码会写只对一些层有用 19.使用GPU训练 方法一 找到这几个部分调用.cuda()然后再返回一个值就行 比如网络模型gzhgzh.cuda() 数据imsimgs.cuda()  targetstargets.cuda()测试集上也要 在每个调用的时候都判断一下 Google colab可以免费用GPU 修改-笔记本设计-硬件加速器GPU 想在像终端输入命令先输入一个 #准备数据集 import timeimport torch.optim.optimizer import torchvision from torch import nn from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriterfrom shizhan.model import Chenzi #准备数据集 train_data torchvision.datasets.CIFAR10(root ../data,trainTrue,transformtorchvision.transforms.ToTensor(),downloadTrue) test_data torchvision.datasets.CIFAR10(root ../data,trainFalse,transformtorchvision.transforms.ToTensor(),downloadTrue) #获得数据集长度 train_data_size len(train_data) test_data_size len(test_data) print(训练数据集的长度为{}.format(train_data_size)) print(测试数据集的长度为{}.format(test_data_size))#利用dataloader加载数据集train_dataloader DataLoader(train_data,64) test_dataloader  DataLoader(test_data,64)#创建网络模型class Chenzi(nn.Module):def __init__(self):super(Chenzi,self).__init__()self.model nn.Sequential(nn.Conv2d(3,32,5,1,2),nn.MaxPool2d(2),nn.Conv2d(32,32,5,1,2),nn.MaxPool2d(2),nn.Conv2d(32,64,5,1,2),nn.MaxPool2d(2),nn.Flatten(),nn.Linear(64*4*4,64),nn.Linear(64,10))def forward(self,x):x self.model(x)return xchenzi Chenzi() chenzi chenzi.cuda() #损失函数 loss_fn nn.CrossEntropyLoss() loss_fn loss_fn.cuda() #优化器 learning_rate 0.01 optimizer torch.optim.SGD(chenzi.parameters(),lr learning_rate)#设置训练网络一些参数 #记录训练次数测试数目和训练轮数 total_train_step 0 total_test_step 0 epoch 30#添加tensorboard writer SummaryWriter(../logs_train) start_time time.time() #多次训练 chenzi.train() for i in range(epoch):# 训练步骤开始print(--------第{}论训练开始---------.format(i1))for data in train_dataloader:imgs,target dataimgs imgs.cuda()target target.cuda()outputs chenzi(imgs)loss loss_fn(outputs,target)#先清零,优化器优化模型optimizer.zero_grad()loss.backward()optimizer.step()total_train_step 1if total_train_step % 100 0:#每逢100输出end_time time.time()# print(时间{}.format(end_time -start_time))print(训练次数{}Loss{}.format(total_train_step,loss.item()))writer.add_scalar(train_loss,loss.item(),total_train_step) #测试步骤开始chenzi.eval()total_test_loss 0total_accuracy 0with torch.no_grad():#没有梯度for data in test_dataloader:imgs,targets dataimgs imgs.cuda()targets targets.cuda()outputs chenzi(imgs)loss loss_fn(outputs,targets)total_test_loss loss.item()#正确率accuracy (outputs.argmax(1) targets).sum()total_accuracy accuracyprint(整体测试集的loss{}.format(total_test_loss))print(整体测试集的正确率{}.format(total_accuracy/test_data_size))writer.add_scalar(test_loss,total_test_loss,total_test_step)writer.add_scalar(test_accuracy,total_accuracy/test_data_size,total_test_step)total_test_step 1#保存每一轮训练的模型torch.save(chenzi,chenzi_{}.pth.format(i))print(模型已保存)writer.close() 方法二 这里可以不另外赋值直接写tudui.to(device) loss_fn一样不需要赋值 imgs,targets一样的方法但是需要赋值 都赋值也没问题 用GPU训练torch.device(“cuda”) torch.device(“cuda0”)单显卡这两种没区别 这样写更好 # chen # 2024/3/18 11:57 # chen # 2024/3/18 0:25 #准备数据集 import torch.optim.optimizer import torchvision from torch import nn from torch.utils.data import DataLoader from torch.utils.tensorboard import SummaryWriterfrom shizhan.model import Chenzi #定义训练设备 device torch.device(cuda) #准备数据集 train_data torchvision.datasets.CIFAR10(root ../data,trainTrue,transformtorchvision.transforms.ToTensor(),downloadTrue) test_data torchvision.datasets.CIFAR10(root ../data,trainFalse,transformtorchvision.transforms.ToTensor(),downloadTrue) #获得数据集长度 train_data_size len(train_data) test_data_size len(test_data) print(训练数据集的长度为{}.format(train_data_size)) print(测试数据集的长度为{}.format(test_data_size))#利用dataloader加载数据集train_dataloader DataLoader(train_data,64) test_dataloader  DataLoader(test_data,64)#创建网络模型 class Chenzi(nn.Module):def __init__(self):super(Chenzi,self).__init__()self.model nn.Sequential(nn.Conv2d(3,32,5,1,2),nn.MaxPool2d(2),nn.Conv2d(32,32,5,1,2),nn.MaxPool2d(2),nn.Conv2d(32,64,5,1,2),nn.MaxPool2d(2),nn.Flatten(),nn.Linear(64*4*4,64),nn.Linear(64,10))def forward(self,x):x self.model(x)return xchenzi Chenzi() chenzi chenzi.to(device) #损失函数 loss_fn nn.CrossEntropyLoss() loss_fn loss_fn.to(device)#优化器 learning_rate 0.01 optimizer torch.optim.SGD(chenzi.parameters(),lr learning_rate)#设置训练网络一些参数 #记录训练次数测试数目和训练轮数 total_train_step 0 total_test_step 0 epoch 10#添加tensorboard writer SummaryWriter(../logs_train) #多次训练 chenzi.train() for i in range(epoch):# 训练步骤开始print(--------第{}论训练开始---------.format(i1))for data in train_dataloader:imgs,target dataimgs imgs.to(device)target target.to(device)outputs chenzi(imgs)loss loss_fn(outputs,target)#先清零,优化器优化模型optimizer.zero_grad()loss.backward()optimizer.step()total_train_step 1if total_train_step % 100 0:#每逢100输出print(训练次数{}Loss{}.format(total_train_step,loss.item()))writer.add_scalar(train_loss,loss.item(),total_train_step) #测试步骤开始chenzi.eval()total_test_loss 0total_accuracy 0with torch.no_grad():#没有梯度for data in test_dataloader:imgs,targets dataimgs imgs.to(device)targets targets.to(device)outputs chenzi(imgs)loss loss_fn(outputs,targets)total_test_loss loss.item()#正确率accuracy (outputs.argmax(1) targets).sum()total_accuracy accuracyprint(整体测试集的loss{}.format(total_test_loss))print(整体测试集的正确率{}.format(total_accuracy/test_data_size))writer.add_scalar(test_loss,total_test_loss,total_test_step)writer.add_scalar(test_accuracy,total_accuracy/test_data_size,total_test_step)total_test_step 1#保存每一轮训练的模型torch.save(chenzi,chenzi_{}.pth.format(i))print(模型已保存)writer.close() 20.完整的模型验证 完整的模型验证测试/demo道路-利用已经训练好的模型然后给它提供输入 # chen # 2024/3/18 12:17 import torch import torchvision from PIL import Image from torch import nnimage_path ../dog/dog.png image Image.open(image_path) print(image) #保证3通道适应PNGJPG image image.convert(RGB) transform torchvision.transforms.Compose([torchvision.transforms.Resize((32,32)),torchvision.transforms.ToTensor()]) image   transform(image) print(image.shape)class Chenzi(nn.Module):def __init__(self):super(Chenzi,self).__init__()self.model nn.Sequential(nn.Conv2d(3,32,5,1,2),nn.MaxPool2d(2),nn.Conv2d(32,32,5,1,2),nn.MaxPool2d(2),nn.Conv2d(32,64,5,1,2),nn.MaxPool2d(2),nn.Flatten(),nn.Linear(64*4*4,64),nn.Linear(64,10))def forward(self,x):x self.model(x)return x #加载 model torch.load(../shizhan/chenzi_9.pth) print(model) image torch.reshape(image,(1,3,32,32)) model.eval() with torch.no_grad():output model(image) print(output) print(output.argmax(1)) 用谷歌gpu训练好以后的保存的模型可以下载下来右键下载再复制到pycharm文件夹下面就行 如果用gpu训练的模型只是用在cpu上测试要在torch.load里写这个