import torch
from torch import nn
classTudui(nn.Module):def__init__(self):super(Tudui, 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),#z展平后大概有64*4*4个像素
nn.Flatten(),
nn.Linear(64*4*4,64),
nn.Linear(64,10))defforward(self,x):
x=self.model(x)return x
#创建一个主方法# if __name__ == '__main__':# tudui=Tudui()# input=torch.ones(64,3,32,32)# output=tudui(input)# print(output.shape)
训练代码
// An highlighted block
import torch
import torchvision.datasets
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
from train_cidair10_model import*
train_data=torchvision.datasets.CIFAR10(root="./data",train=True,transform=torchvision.transforms.ToTensor(),
download=True)
test_data=torchvision.datasets.CIFAR10(root="./data",train=False,transform=torchvision.transforms.ToTensor(),
download=True)#len 获得数据集的长度
train_data_size=len(train_data)
test_data_size=len(test_data)#字符串格式化,将变量train_data_size替换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,batch_size=64)
test_dataloader=DataLoader(test_data,batch_size=64)#搭建神经网络(CIFAR10有十个类别,所以此网络应该是10分类),挪到train_cidair10_model.py文件中#创建网络模型
tudui=Tudui()#创建损失函数
loss_fuun=nn.CrossEntropyLoss()#定义优化器#1e-2=1*(10)^(-2)=1/100=0.01
learning_rate=1e-2
optimi=torch.optim.SGD(tudui.parameters(),lr=learning_rate)#设置训练网络的一些参数#记录训练的次数
total_train_step=0#记录测试的次数
total_test_step=0#训练的轮数
epoch=10for i inrange(epoch):print("-----------第{}轮训练----------".format(i+1))#训练开始for data in train_dataloader:
img,tagets=data
output=tudui(img)#tagets是本来的样本类别,output是训练后得出的样本类别
loss=loss_fuun(output,tagets)#优化器优化模型
optimi.zero_grad()
loss.backward()
optimi.step()
total_train_step=total_train_step+1if total_train_step%100==0:print("训练次数:{},loss:{}".format(total_train_step,loss.item()))
添加测试代码
with torch.no_grad():for data in test_dataloader:
img,target=data
output=tudui(img)
loss=loss_fuun(output,target)
total_test_loss+=loss
print("整体数据集的loss是:{}".format(total_test_loss))
使用tensorboard显示
#添加tensorboard
writer=SummaryWriter("./log_train_loss")...for i inrange(epoch):print("-----------第{}轮训练----------".format(i+1))#训练开始for data in train_dataloader:
img,tagets=data
output=tudui(img)#tagets是本来的样本类别,output是训练后得出的样本类别
loss=loss_fuun(output,tagets)#优化器优化模型
optimi.zero_grad()
loss.backward()
optimi.step()
total_train_step=total_train_step+1if total_train_step%100==0:print("训练次数:{},loss:{}".format(total_train_step,loss.item())) writer.add_scalar("train_loss",loss.item(),total_train_step)#此处代码就没有调优
total_test_loss=0with torch.no_grad():for data in test_dataloader:
img,target=data
output=tudui(img)
loss=loss_fuun(output,target)
total_test_loss+=loss
print("整体数据集的loss是:{}".format(total_test_loss))
writer.add_scalar("test_loss",total_test_loss,total_test_step)
total_test_step+=1#保存每一轮训练的模型
torch.save(tudui,"tudui_{}.pth".format(i))print("模型已保存")
writer.close()
完整训练、测试代码(部分优化代码)
import torch
import torchvision.datasets
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
from train_cidair10_model import*
train_data=torchvision.datasets.CIFAR10(root="./data",train=True,transform=torchvision.transforms.ToTensor(),
download=True)
test_data=torchvision.datasets.CIFAR10(root="./data",train=False,transform=torchvision.transforms.ToTensor(),
download=True)#len 获得数据集的长度
train_data_size=len(train_data)
test_data_size=len(test_data)#字符串格式化,将变量train_data_size替换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,batch_size=64)
test_dataloader=DataLoader(test_data,batch_size=64)#搭建神经网络(CIFAR10有十个类别,所以此网络应该是10分类),挪到train_cidair10_model.py文件中#创建网络模型
tudui=Tudui()#创建损失函数
loss_fuun=nn.CrossEntropyLoss()#定义优化器#1e-2=1*(10)^(-2)=1/100=0.01
learning_rate=1e-2
optimi=torch.optim.SGD(tudui.parameters(),lr=learning_rate)#设置训练网络的一些参数#记录训练的次数
total_train_step=0#记录测试的次数
total_test_step=0#训练的轮数
epoch=10#添加tensorboard
writer=SummaryWriter("./log_train_loss")for i inrange(epoch):print("-----------第{}轮训练----------".format(i+1))#训练开始for data in train_dataloader:
img,tagets=data
output=tudui(img)#tagets是本来的样本类别,output是训练后得出的样本类别
loss=loss_fuun(output,tagets)#优化器优化模型
optimi.zero_grad()
loss.backward()
optimi.step()
total_train_step=total_train_step+1if total_train_step%100==0:print("训练次数:{},loss:{}".format(total_train_step,loss.item()))
writer.add_scalar("train_loss",loss.item(),total_train_step)#测试步骤的开始#此处代码就没有调优
total_test_loss=0#整体正确率
total_accuracy=0with torch.no_grad():for data in test_dataloader:
img,target=data
output=tudui(img)
loss=loss_fuun(output,target)
total_test_loss+=loss
accuracy=(output.argmax(1)==target).sum()
total_accuracy+=accuracy
print("整体数据集的loss是:{}".format(total_test_loss))print("整体测试集上的正确率是:{}",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(tudui,"tudui_{}.pth".format(i))print("模型已保存")
writer.close()