当前位置： 首页 > news >正文

做网站策划营销推广,时事新闻,公众号采集wordpress,网站建设网站结构图PyTorch学习#xff08;1#xff09; CIFAR-10数据集-图像分类 数据集来源是官方提供的#xff1a; torchvision.datasets.CIFAR10()共有十类物品#xff0c;需要用CNN实现图像分类问题。 代码如下#xff1a;(CIFAR_10_Classifier_Self_1.py) import torch import t…PyTorch学习1 CIFAR-10数据集-图像分类 数据集来源是官方提供的 torchvision.datasets.CIFAR10()共有十类物品需要用CNN实现图像分类问题。 代码如下(CIFAR_10_Classifier_Self_1.py) import torch import torchvision from torch import optim from torch.utils.data import DataLoader import torch.nn as nn import torch.nn.functional as F from torchvision.transforms import transforms import matplotlib as plttransform transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))] )train_set torchvision.datasets.CIFAR10(root./CIFAR_10, trainTrue, transformtransform,downloadTrue) test_set torchvision.datasets.CIFAR10(root./CIFAR_10, trainFalse, transformtransform,downloadTrue)train_loader torch.utils.data.DataLoader(datasettrain_set, batch_size4, shuffleTrue) # shuffle: 打乱数据集顺序 test_loader torch.utils.data.DataLoader(datasettest_set, batch_size4, shuffleTrue)classes (plane, car, bird, cat, deer, dog, frog, horse, ship, truck) # CIFAR-10 targetsclass MyNet(nn.Module):def init(self):super().init() # 初始化父类self.conv1 nn.Conv2d(in_channels3, out_channels6, kernel_size5)self.pool nn.MaxPool2d(kernel_size2)self.conv2 nn.Conv2d(in_channels6, out_channels16, kernel_size5)self.fc1 nn.Linear(in_features16*5*5, out_features120)self.fc2 nn.Linear(in_features120, out_features84)self.fc3 nn.Linear(in_features84, out_features10)def forward(self, x):x self.pool(F.relu(self.conv1(x))) # 卷积层后面通常接非线性变换x self.pool(F.relu(self.conv2(x)))x torch.flatten(x, 1)x F.relu(self.fc1(x))x F.relu(self.fc2(x))x self.fc3(x)return xnet MyNet()criterion nn.CrossEntropyLoss()

optimizer: 优化器 SGD: 随机梯度下降

optimizer optim.SGD(net.parameters(), lr0.001, momentum0.9)for epoch in range(2): # 训练进行两个epoch每个epoch都代表一次完整的数据集遍历running_loss 0.0for i, data in enumerate(train_loader, 0): # 遍历数据加载器(DataLoader)inputs, labels dataoptimizer.zero_grad()outputs net(inputs)loss criterion(outputs, labels)loss.backward()optimizer.step()running_loss loss.item()if i % 2000 1999:print(f[{epoch 1}, {i 1:5d}] loss: {running_loss / 2000:.3f})running_loss 0.0 print(Finished Training)# save PATH ./cifar_net.pth torch.save(net, PATH)运行结果 C:\Users\dell\anaconda3\envs\pytorch\python.exe C:\Users\dell\Desktop\2024Summer\project1\learn_pytorch\pythonProject3\CIFAR_10_Classifier_Self_1.py Files already downloaded and verified Files already downloaded and verified [1, 2000] loss: 2.208 [1, 4000] loss: 1.849 [1, 6000] loss: 1.681 [1, 8000] loss: 1.569 [1, 10000] loss: 1.523 [1, 12000] loss: 1.477 [2, 2000] loss: 1.395 [2, 4000] loss: 1.373 [2, 6000] loss: 1.360 [2, 8000] loss: 1.306 [2, 10000] loss: 1.325 [2, 12000] loss: 1.297 Finished TrainingProcess finished with exit code 0把上面程序中的epoch循环次数改为10并运行下列程序(CIFAR_10_Classifier_Self_2.py) import torch from CIFAR_10_Classifier_Self_1 import MyNet import torchvision.transforms as transforms from PIL import Imagenet MyNet() PATH ./cifar_net.pth net.load_state_dict(torch.load(PATH)) net.eval()transform transforms.Compose([transforms.Resize((32, 32)), # 输入不符合网络要求时会报错transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)) ])# read image def image_loader(image_name):image Image.open(image_name)image transform(image).unsqueeze(0) # 在tensor外面套一层中括号[]return imagedef classify_image(image_path):image image_loader(imagepath)outputs net(image), predicted torch.max(outputs, 1)return predicted.item()image_path ./images/ALPINA B3.jpg predicted_class classify_image(image_path) classes (plane, car, bird, cat, deer, dog, frog, horse, ship, truck) print(Predicted Class:, classes[predicted_class])对于输入图像(ALPINA B3.jpg) 运行结果如下 C:\Users\dell\anaconda3\envs\pytorch\python.exe C:\Users\dell\Desktop\2024Summer\project1\learn_pytorch\pythonProject3\CIFAR_10_Classifier_Self_2.py Files already downloaded and verified Files already downloaded and verified [1, 2000] loss: 2.227 [1, 4000] loss: 1.900 [1, 6000] loss: 1.696 [1, 8000] loss: 1.586 [1, 10000] loss: 1.518 [1, 12000] loss: 1.440 [2, 2000] loss: 1.386 [2, 4000] loss: 1.351 [2, 6000] loss: 1.342 [2, 8000] loss: 1.312 [2, 10000] loss: 1.293 [2, 12000] loss: 1.246 [3, 2000] loss: 1.194 [3, 4000] loss: 1.199 [3, 6000] loss: 1.180 [3, 8000] loss: 1.175 [3, 10000] loss: 1.150 [3, 12000] loss: 1.154 [4, 2000] loss: 1.070 [4, 4000] loss: 1.088 [4, 6000] loss: 1.099 [4, 8000] loss: 1.069 [4, 10000] loss: 1.101 [4, 12000] loss: 1.082 [5, 2000] loss: 0.988 [5, 4000] loss: 1.013 [5, 6000] loss: 1.024 [5, 8000] loss: 1.040 [5, 10000] loss: 1.033 [5, 12000] loss: 1.045 [6, 2000] loss: 0.944 [6, 4000] loss: 0.957 [6, 6000] loss: 0.978 [6, 8000] loss: 0.990 [6, 10000] loss: 0.976 [6, 12000] loss: 0.998 [7, 2000] loss: 0.891 [7, 4000] loss: 0.931 [7, 6000] loss: 0.945 [7, 8000] loss: 0.934 [7, 10000] loss: 0.936 [7, 12000] loss: 0.936 [8, 2000] loss: 0.851 [8, 4000] loss: 0.898 [8, 6000] loss: 0.907 [8, 8000] loss: 0.898 [8, 10000] loss: 0.890 [8, 12000] loss: 0.911 [9, 2000] loss: 0.809 [9, 4000] loss: 0.851 [9, 6000] loss: 0.856 [9, 8000] loss: 0.869 [9, 10000] loss: 0.888 [9, 12000] loss: 0.903 [10, 2000] loss: 0.796 [10, 4000] loss: 0.812 [10, 6000] loss: 0.825 [10, 8000] loss: 0.857 [10, 10000] loss: 0.865 [10, 12000] loss: 0.862 Finished Training Predicted Class: carProcess finished with exit code 0可以看到能够将图片正确分类。 之前epoch为2时错误地将图片分类成了ship推测是网络参数因为训练次数少导致并非较佳值epoch为10时也不敢保证一定能预测正确 MNIST手写数字识别(LeNet) import torch import numpy as np from matplotlib import pyplot as plt from torch import nn from torch.utils.data import DataLoader from torchvision import transforms from torchvision import datasets import torch.nn.functional as Ftransform transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.1307,), (0.3081,)) ])# Fetch the dataset training_set datasets.MNIST(root./minst, trainTrue, transformtransform, downloadTrue) train_loader DataLoader(datasettraining_set, batch_size64, shuffleTrue)test_set datasets.MNIST(root./minst, trainFalse, transformtransform, downloadTrue) test_loader DataLoader(datasettest_set, batch_size64, shuffleTrue)# show the dataset * fig plt.figure() for i in range(12):plt.subplot(3, 4, i1) # 第一个参数代表子图的行数第二个参数代表该行图像的列数第三个参数代表每行的第几个图像plt.tight_layout()plt.imshow(training_set.data[i], cmapgray, interpolationnone)plt.title(Label: {}.format(training_set.targets[i]))plt.xticks([])plt.yticks([]) plt.show()class MyLeNet5(nn.Module):def init(self):super(MyLeNet5, self).init()self.c1 nn.Conv2d(in_channels1, out_channels6, kernel_size5, padding2)self.Sigmoid nn.Sigmoid()self.s2 nn.AvgPool2d(kernel_size2)self.c3 nn.Conv2d(in_channels6, out_channels16, kernel_size5)self.s4 nn.AvgPool2d(kernel_size2)self.c5 nn.Conv2d(in_channels16, out_channels120, kernel_size5)self.flatten nn.Flatten()self.f6 nn.Linear(in_features120, out_features84)self.output nn.Linear(in_features84, out_features10)def forward(self, x):x self.Sigmoid(self.c1(x))x self.s2(x)x self.Sigmoid(self.c3(x))x self.s4(x)x self.c5(x)x self.flatten(x)x self.f6(x)x self.output(x)return xmodel MyLeNet5()# loss function optimizer参数优化 criterion torch.nn.CrossEntropyLoss() optimizer torch.optim.SGD(paramsmodel.parameters(), lr0.01, momentum0.5) # momentum: 冲量# train def train(epoch): # epoch: 方便打印running_loss 0.0running_total 0running_correct 0for batch_idx, data in enumerate(train_loader, 0): # 给train_loader元素编号从0开始inputs, targets data # inputs和targets是“数组”的形式optimizer.zero_grad() # 消除优化器中原有的梯度outputs model(inputs)loss criterion(outputs, targets) # 对比输出结果和“答案”loss.backward()optimizer.step() # 优化网络参数runningloss loss.item() # .item(): 取出tensor中特定位置的具体元素值并返回该值(Tensor to int or float), predicted torch.max(outputs.data, dim1) # 找到每个样本预测概率最高的类别的标签值即预测结果# dim0计算tensor中每列的最大值的索引dim1表示每行的最大值的索引running_total inputs.shape[0] # .shape[0]: 读取矩阵第一维度的长度running_correct (predicted targets).sum().item()if batch_idx % 300 299:print([%d, %5d]: loss: %.3f , acc: %.2f %%% (epoch 1, batch_idx 1, running_loss / 300, 100 * running_correct / running_total))running_loss 0.0running_total 0running_correct 0# test * def test(epoch):correct 0total 0with torch.no_grad():for data in testloader:images, labels dataoutputs model(images), predicted torch.max(outputs.data, dim1)total labels.size(0)correct (predicted labels).sum().item()acc correct / totalprint([%d / %d]: Accuracy on test set: %.1f %% % (epoch 1, 10, 100 * acc))return accacc_list_test [] for epoch in range(10):train(epoch)acc_test test(epoch)acc_list_test.append(acc_test)plt.plot(acc_list_test) plt.xlabel(Epoch) plt.ylabel(Accuracy on Test Set) plt.show()运行结果 C:\Users\dell\anaconda3\envs\pytorch\python.exe C:\Users\dell\Desktop\2024Summer\project1\learn_pytorch\pythonProject3\MINST_1.py [1, 300]: loss: 2.302 , acc: 11.04 % [1, 600]: loss: 2.297 , acc: 11.97 % [1, 900]: loss: 2.287 , acc: 15.71 % [1 / 10]: Accuracy on test set: 26.9 % [2, 300]: loss: 2.212 , acc: 27.77 % [2, 600]: loss: 1.695 , acc: 50.16 % [2, 900]: loss: 0.959 , acc: 71.32 % [2 / 10]: Accuracy on test set: 77.0 % [3, 300]: loss: 0.655 , acc: 79.78 % [3, 600]: loss: 0.558 , acc: 82.46 % [3, 900]: loss: 0.503 , acc: 84.27 % [3 / 10]: Accuracy on test set: 86.3 % [4, 300]: loss: 0.431 , acc: 86.77 % [4, 600]: loss: 0.413 , acc: 87.64 % [4, 900]: loss: 0.391 , acc: 88.16 % [4 / 10]: Accuracy on test set: 89.3 % [5, 300]: loss: 0.361 , acc: 89.16 % [5, 600]: loss: 0.354 , acc: 89.33 % [5, 900]: loss: 0.330 , acc: 89.92 % [5 / 10]: Accuracy on test set: 90.4 % [6, 300]: loss: 0.322 , acc: 90.38 % [6, 600]: loss: 0.322 , acc: 90.20 % [6, 900]: loss: 0.306 , acc: 90.59 % [6 / 10]: Accuracy on test set: 91.5 % [7, 300]: loss: 0.296 , acc: 90.87 % [7, 600]: loss: 0.293 , acc: 91.23 % [7, 900]: loss: 0.290 , acc: 91.17 % [7 / 10]: Accuracy on test set: 92.1 % [8, 300]: loss: 0.279 , acc: 91.47 % [8, 600]: loss: 0.274 , acc: 91.71 % [8, 900]: loss: 0.263 , acc: 92.03 % [8 / 10]: Accuracy on test set: 92.6 % [9, 300]: loss: 0.252 , acc: 92.34 % [9, 600]: loss: 0.253 , acc: 92.16 % [9, 900]: loss: 0.250 , acc: 92.61 % [9 / 10]: Accuracy on test set: 93.3 % [10, 300]: loss: 0.240 , acc: 92.69 % [10, 600]: loss: 0.230 , acc: 93.27 % [10, 900]: loss: 0.230 , acc: 93.03 % [10 / 10]: Accuracy on test set: 93.6 % 问题区 import torchvision 和 from torchvision import * 有什么区别 import torchvision # 使用transforms模块
transform torchvision.transforms.Compose([…])from torchvision import * # 直接使用transforms模块如果torchvision中有这样的公开导入

注意实际上torchvision不会将所有内容都直接暴露出来这里只是为了说明

transform Compose([…])然而第二种方法可能会出现命名冲突的问题。同时并非所有内容都会被采用第二种方法读入以_开头的“私有”名称通常不会被导入。 因此推荐使用 import torchvision 的方式。 DataLoader返回的是啥为什么有时候要在外面套一个“enumerate()” 返回值是一个实现了iter的对象可以使用for循环进行迭代或者转换成迭代器取第一条batch数据查看。

train

def train(epoch):…for batch_idx, data in enumerate(train_loader, 0):…在上面这段代码中需要在train_loader外面套个enumerate的原因是能够给train_loader加上编号变成“batch_idx”。这里是方便打印训练结果 Python enumerate()函数使用举例 seq [one, two, three]for i, element in enumerate(seq): … print i, element … 0 one 1 two 2 threetorch.max()的作用 用法如下 import torchoutput torch.tensor([[1, 2, 3], [3, 4, 5]]) predict torch.max(output, dim0) # dim0: 取每一列的最大值 print(predict) predict torch.max(output, dim1) # dim1: 取每一行的最大值 print(predict)输出 torch.return_types.max( valuestensor([3, 4, 5]), indicestensor([1, 1, 1]))torch.return_types.max( valuestensor([3, 5]), indicestensor([2, 2]))indices表示从0开始的下标。 _, predicted torch.max(outputs.data, dim1) 这里的下划线的作用是 下划线表示一个占位符表示该值被有意地忽略。