当前位置： 首页 > news >正文

seo运营培训,北京seowyhseo,广州网站建设藤虎,电子商务论文5000字前言 一直就听说学习深度学习无非就是看论文#xff0c;然后复现#xff0c;不断循环#xff0c;这段时间也看了好几篇论文(虽然都是简单的)#xff0c;但是对于我一个人自学#xff0c;复现成功#xff0c;我感觉还是挺开心的 本人初学看论文的思路#xff1a;聚焦网络…前言 一直就听说学习深度学习无非就是看论文然后复现不断循环这段时间也看了好几篇论文(虽然都是简单的)但是对于我一个人自学复现成功我感觉还是挺开心的 本人初学看论文的思路聚焦网络结构与其实验的效果 LeNet虽然简单很老了但是毕竟经典对于初学的的我来说我感觉还是很有必要学习的可以积累CNN网络结构模型注意minist数据集可以直接下载不用自己找详情请看导入数据 本来今天打算更新C从C的变化基础的但是由于种种原因就先更新这篇吧 论文(知网可查询)基于LeNet-5的手写数字识别的改进方法 网络结构(LeNet) 卷积层两层 池化层两层 卷积层参数 第一层维度变化(1-6)步伐1卷积核5 * 5第二层维度变化(6-16)步伐1卷积核5 * 5 池化层 两层都是卷积核2 * 2步伐2 全连接层3层 16 * 5 * 5 – 120 – 84 – 10 网络结构图如下(论文截图)
结果 轮次10有点大了可以降低相比第一课发现在训练集的损失率、测试集的损失率、训练集的准确率都有提升详情情况结果可视化 1、前期准备 1、设置GPU import torch # 用于张量计算和自动求导 import torch.nn as nn # 构建神经网络和损失函数 import matplotlib.pyplot as plt # 绘图 import torchvision # 专门处理视觉的库# 设置GPU device torch.device(cuda if torch.cuda.is_available() else cpu) print(device) print(torch.version) print(torchvision.version)cuda 2.4.0 0.19.02、导入数据

将所有的数据图片统一格式, 论文大小为32 * 32

from torchvision import transforms, datasets transforms transforms.Compose([transforms.Resize([32, 32]), # 统一图片大小transforms.ToTensor(), # 统一规格transforms.Normalize(mean[0.1307], std[0.3081]) # MNIST的均值和方差 ])# download设置为True可以自动下载图片 train_ds torchvision.datasets.MNIST(data, trainTrue, transformtransforms, downloadFalse)test_ds torchvision.datasets.MNIST(data, trainTrue, transformtransforms, downloadFalse)batch_size 32 train_dl torch.utils.data.DataLoader(train_ds, batch_sizebatch_size, shuffleTrue)test_dl torch.utils.data.DataLoader(test_ds, batch_sizebatch_size, shuffleTrue)# 取一个批次查看数据格式

数据的shape为[batch_size, channel, heigh, weight]

batch_size是自己设定的channelheightweight分别是图片的通道数高度宽度

imgs, labels next(iter(train_dl)) imgs.shape结果 torch.Size([32, 1, 32, 32])3、数据可视化 import numpy as np# 指定图片的大小图像的大小为20宽5高 plt.figure(figsize(20,5)) for i, imgs in enumerate(imgs[:20]):# 维度缩减npimg np.squeeze(imgs.numpy())# 将整个figure分层2行10列绘制第i1个子图plt.subplot(2, 10, i 1)plt.imshow(npimg, cmapplt.cm.binary)plt.axis(off)​
​ 2、构建简单的CNN网络 import torch.nn.functional as Fnum_classes 10 # 图片的类别数class Model(nn.Module):def init(self):super().init()# 特征提取网络设置self.conv1 nn.Conv2d(1, 6, kernel_size5) self.pool1 nn.MaxPool2d(2) self.conv2 nn.Conv2d(6, 16, kernel_size5) self.pool2 nn.MaxPool2d(2) # 分类网络设置self.fc1 nn.Linear(16 * 5 * 5, 120)self.fc2 nn.Linear(120, 84)self.fc3 nn.Linear(84, num_classes)# 前向传播def forward(self, x):x F.relu(self.conv1(x))x self.pool1(x)x F.relu(self.conv2(x))x self.pool2(x)x x.view(-1, 16 * 5 * 5)x F.relu(self.fc1(x))x F.relu(self.fc2(x))x self.fc3(x)return x 加载并且打印模型 from torchinfo import summary# 将模型转移到GPU中 model Model().to(device)summary(model)Layer (type:depth-idx) Param #Model – ├─Conv2d: 1-1 156 ├─MaxPool2d: 1-2 – ├─Conv2d: 1-3 2,416 ├─MaxPool2d: 1-4 – ├─Linear: 1-5 48,120 ├─Linear: 1-6 10,164 ├─Linear: 1-7 850Total params: 61,706 Trainable params: 61,706 Non-trainable params: 0for X, y in train_dl:print(X.shape) # 检查输入数据的形状break # 只打印第一个批次的数据形状torch.Size([32, 1, 32, 32])3、模型训练 1、设置超参数 loss_fn nn.CrossEntropyLoss() # 创建损失函数 learn_rate 1e-2 # 学习率 opt torch.optim.SGD(model.parameters(), lr learn_rate) 2、编写训练函数 def train(dataloader, model, loss_fn, optimizer):size len(dataloader.dataset) # 训练集大小一共60000张图片num_batchs len(dataloader) # 批次数目1875 (⁶⁰⁰⁰⁰⁄₃₂)train_loss, train_acc 0, 0 # 初始化训练损失和正确率for X, y in dataloader: # 获取图片及其标签X, y X.to(device), y.to(device) # 计算预测误差pred model(X) # 网络输出loss loss_fn(pred, y) # 计算网络输出和真实值的差距# 反向传播optimizer.zero_grad() # gred属性归零loss.backward() # 反向传播optimizer.step() # 每一步自动跟新# 记录acc和losstrain_acc (pred.argmax(1) y).type(torch.float).sum().item()train_loss loss.item()train_acc / sizetrain_loss / num_batchsreturn train_acc, train_loss 3、编写测试函数 def test(dataloader, model, loss_fn):size len(dataloader.dataset) # 测试集的大小一共10000张图片num_batches len(dataloader) # 批次数目31310000/32 321.5向上取整test_loss, test_acc 0, 0# 当不进行训练时候停止梯度更新节省计算内存消耗with torch.no_grad():for imgs, target in dataloader:imgs, target imgs.to(device), target.to(device)# 计算losstarget_pred model(imgs)loss loss_fn(target_pred, target)test_loss loss.item()test_acc (target_pred.argmax(1) target).type(torch.float).sum().item()test_acc / sizetest_loss / num_batchesreturn test_acc, test_loss 4、正式训练 epochs 10 train_loss [] train_acc [] test_loss [] test_acc []for epoch in range(epochs):model.train()epoch_train_acc, epoch_train_loss train(train_dl, model, loss_fn, opt)model.eval()epoch_test_acc, epoch_test_loss test(test_dl, model, loss_fn)train_acc.append(epoch_train_acc)train_loss.append(epoch_train_loss)test_acc.append(epoch_test_acc)test_loss.append(epoch_test_loss)template (Eopch: {:2d}, Train_acc: {:.1f}%, Train_loss: {:.3f}, Test_acc: {:.1f}%, test_loss: {:.3f})print(template.format(epoch1, epoch_train_acc * 100, epoch_train_loss, epoch_test_acc, epoch_test_loss))print(Done)Eopch: 1, Train_acc: 75.9%, Train_loss: 0.739, Test_acc: 1.0%, test_loss: 0.144 Eopch: 2, Train_acc: 96.4%, Train_loss: 0.117, Test_acc: 1.0%, test_loss: 0.079 Eopch: 3, Train_acc: 97.6%, Train_loss: 0.080, Test_acc: 1.0%, test_loss: 0.073 Eopch: 4, Train_acc: 98.0%, Train_loss: 0.063, Test_acc: 1.0%, test_loss: 0.056 Eopch: 5, Train_acc: 98.4%, Train_loss: 0.053, Test_acc: 1.0%, test_loss: 0.048 Eopch: 6, Train_acc: 98.5%, Train_loss: 0.047, Test_acc: 1.0%, test_loss: 0.041 Eopch: 7, Train_acc: 98.7%, Train_loss: 0.042, Test_acc: 1.0%, test_loss: 0.035 Eopch: 8, Train_acc: 98.8%, Train_loss: 0.037, Test_acc: 1.0%, test_loss: 0.029 Eopch: 9, Train_acc: 99.0%, Train_loss: 0.033, Test_acc: 1.0%, test_loss: 0.029 Eopch: 10, Train_acc: 99.0%, Train_loss: 0.030, Test_acc: 1.0%, test_loss: 0.023 Done4、结果可视化 import matplotlib.pyplot as plt import warnings

忽略警告

warnings.filterwarnings(ignore) #忽略警告信息 plt.rcParams[font.sans-serif] [SimHei] # 用来正常显示中文标签 plt.rcParams[axes.unicode_minus] False # 用来正常显示负号 plt.rcParams[figure.dpi] 100 #分辨率epochs_range range(epochs)plt.figure(figsize(12, 3)) plt.subplot(1, 2, 1)plt.plot(epochs_range, train_acc, labelTraining Accuracy) plt.plot(epochs_range, test_acc, labelTest Accuracy) plt.legend(loclower right) plt.title(Training and Validation Accuracy)plt.subplot(1, 2, 2) plt.plot(epochs_range, train_loss, labelTrain Loss) plt.plot(epochs_range, test_loss, labelTest Loss) plt.legend(locupper right) plt.title(Training and Validation Loss) plt.show()​
​