文章目录

（一）概述

（二）数据预处理

（三）构建网络

（四）选择优化器

（五）训练测试加保存模型

正文

1、CIFAR-10 数据集包含 10 个类别的 60000 个 32x32 彩色图像，每个类别有 6000 张图像。有 50000 张训练图像和 10000 张测试图像。
2、数据集分为五个训练批次和一个测试批次，每个批次具有 10000 张图像。测试集包含从每个类别中 1000 张随机选择的图像。剩余的图像按照随机顺序构成 5 个批次的训练集，每个批次中各类图像的数量不相同，但总训练集中每一类都正好有 5000 张图片
3、数据集中的 class(类)，以及每个 class 的 10 个随机图像：

CNN：AlexNet的原理与构建 - 图1

1、引入包库

  1. import torch 
  2. import numpy as np from torch.utils.data
  3. import  DataLoader  from torchvision 
  4. import datasets,transforms 
  5. import torch.nn as nn 
  6. import torch.nn.functional as F 
  7. import os 
  8. import time

2、定义超参数

  1. #定义超参数 batch_size=100 learning_rate=1e-2 epochs=200

3、标准化

  1. data_tf=transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5,0.5,0.5),(0.5,0.5,0.5))])

4、读取数据

  1. train_data = datasets.CIFAR10(root='./data',train=True,transform=data_tf,download=False) test_data = datasets.CIFAR10(root='./data',train=False,transform=data_tf)

5、装载数据

  1. train_loader=DataLoader(train_data,batch_size=batch_size,shuffle=True) test_loader=DataLoader(test_data,batch_size=batch_size,shuffle=True)

代码

  1. class  Alexnet(nn.Module):  def __init__(self): super(Alexnet, self).__init__() self.conv1 = nn.Conv2d(3,64,3,2,1) self.pool = nn.MaxPool2d(3,  2) self.conv2 = nn.Conv2d(64,192,  5,  1,  2) self.conv3 = nn.Conv2d(192,  384,  3,  1,  1) self.conv4 = nn.Conv2d(384,256,  3,  1,  1) self.conv5 = nn.Conv2d(256,256,  3,  1,  1) self.drop = nn.Dropout(0.5) self.fc1 = nn.Linear(256*6*6,  4096) self.fc2 = nn.Linear(4096,  4096) self.fc3 = nn.Linear(4096,  1000)  def forward(self, x): x = self.pool(F.relu(self.conv1(x))) x = self.pool(F.relu(self.conv2(x))) x = F.relu(self.conv3(x)) x = F.relu(self.conv4(x)) x = self.pool(F.relu(self.conv5(x))) x = x.view(-1, self.num_flat_features(x)) x = F.relu(self.fc1(x)) x = self.drop(F.relu(self.fc1(x))) x = self.drop(F.relu(self.fc2(x))) x = self.fc3(x)  return x

网络结构

CNN：AlexNet的原理与构建 - 图2

model=AlexNet()  #定义loss与参数更新 criterion=nn.CrossEntropyLoss() optimizer=torch.optim.SGD(model.parameters(),lr=learning_rate)

#训练  for epoch in range(epochs): total =  0 running_loss =  0.0 running_correct =  0  print("epoch {}/{}".format(epoch, epochs))  print("-"  *  10)  for data in train_loader: img, label = data

        img =  Variable(img)  if torch.cuda.is_available(): img = img.cuda() label = label.cuda()  else: img =  Variable(img) label =  Variable(label) out = model(img)  # 得到前向传播的结果 loss = criterion(out, label)  # 得到损失函数 print_loss = loss.data.item() optimizer.zero_grad()  # 归0梯度 loss.backward()  # 反向传播 optimizer.step()  # 优化 running_loss += loss.item() epoch +=  1  if epoch %  50  ==  0:  print('epoch:{},loss:{:.4f}'.format(epoch, loss.data.item())) _, predicted = torch.max(out.data,  1) total += label.size(0) running_correct +=  (predicted == label).sum()  print('第%d个epoch的识别准确率为：%d%%'  %  (epoch +  1,  (100  * running_correct / total)))

标签： 10,nn,loss,self,epoch,cifar,label,pytorch,data
来源： https://blog.csdn.net/MosterSakura/article/details/115441316
https://www.icode9.com/content-4-915122.html