import torch.optim.sgd
import torchvision
# 准备数据集
from torch import nn
from torch.utils.data import DataLoader
from torch.utils.tensorboard import SummaryWriter
# 定义训练的设备
device=torch.device('cpu')
writer=SummaryWriter('./log_train')
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)
train_data_size=len(train_data)
test_data_size=len(test_data)
# 格式化字符串
print('训练数据集长度{}'.format(train_data_size))
print('测试数据集长度{}'.format(test_data_size))
# 利用dataloader来加载数据集
train_dataloader=DataLoader(train_data,batch_size=64)
test_dataloader=DataLoader(test_data,batch_size=64)
# 搭建神经网络
class li(nn.Module):
def __init__(self):
super(li, 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
LI=li()
LI=LI.to(device)
# 创建损失函数
loss_fn=nn.CrossEntropyLoss()
loss_fn=loss_fn.to(device)
# 优化器
learning_rate=0.01
optimizer=torch.optim.SGD(LI.parameters(),lr=learning_rate)
# 设置训练网络的一些参数
# 记录训练次数
total_train_step=0
# 记录测试次数
total_test_step=0
# 训练的轮数
epoch=20
for i in range(epoch):
print('---------第{}轮开始'.format(i+1))
# 训练开始
LI.train()
for data in train_dataloader:
imgs,targets=data
imgs=imgs.to(device)
targets=targets.to(device)
outputs=LI(imgs)
loss=loss_fn(outputs,targets)
optimizer.zero_grad()
loss.backward()#梯度下降计算新的梯度
optimizer.step()
total_train_step=total_train_step+1
if total_train_step%100==0:
print('训练次数{},loss{}'.format(total_train_step,loss))
writer.add_scalar('train_loss',loss.item(),total_train_step)
# 测试步骤
LI.eval() #调用模块
total_test_loss=0
total_accuracy=0
with torch.no_grad():
for data in test_dataloader:
imgs,targets=data
imgs = imgs.to(device)
targets = targets.to(device)
outputs=LI(imgs)
loss=loss_fn(outputs,targets)
total_test_loss=total_test_loss+loss.item()
accuracy=(outputs.argmax(1)==targets).sum()
total_accuracy+=accuracy
print('整体loss{}'.format(total_test_loss))
print('zhengquelv-整体:{}'.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
torch.save(LI,'li{}.pth'.format(i))
print('saved')
writer.close()