模型搭建部分
import torch
from torch import nn
from torch.nn import Sequential, Conv2d, MaxPool2d, Flatten, Linear
class MyNet(nn.Module):
def __init__(self):
super(MyNet, self).__init__()
self.model=Sequential(
Conv2d(in_channels=3, out_channels=32, kernel_size=5, padding=2),
MaxPool2d(2),
Conv2d(32, 32, 5, padding=2),
MaxPool2d(2),
Conv2d(32, 64, 5, padding=2),
MaxPool2d(2),
Flatten(),
Linear(1024, 64),
Linear(64, 10)
)
def forward(self, x):
x=self.model(x)
return x
if __name__ == '__main__':
mynet=MyNet()
input=torch.ones((64,3,32,32))
output=mynet(input)
print(output.shape)
训练和测试部分
import torchvision
from torch.utils.tensorboard import SummaryWriter
from model import *
from torch.utils.data import DataLoader
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)
print("训练集的长度为{}".format(train_data_size))
print("测试集的长度为{}".format(test_data_size))
train_dataloader=DataLoader(train_data,batch_size=64)
test_dataloader=DataLoader(test_data,batch_size=64)
mynet=MyNet()
loss_fn=nn.CrossEntropyLoss()
learning_rate=0.01
optimizer=torch.optim.SGD(mynet.parameters(),lr=learning_rate)
total_train_step=0
total_test_step=0
epoch=20
writer=SummaryWriter("logs")
for i in range(epoch):
print("------第{}轮训练开始-------".format(i))
mynet.train()
for data in train_dataloader:
imgs,targets=data
outputs=mynet(imgs)
loss=loss_fn(outputs,targets)
optimizer.zero_grad()
loss.backward()
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.item()))
writer.add_scalar("train_loss",loss.item(),total_train_step)
mynet.eval()
total_test_loss=0
total_accurary=0
for data in test_dataloader:
imgs,targets=data
outputs=mynet(imgs)
loss=loss_fn(outputs,targets)
total_test_loss=total_test_loss+loss
accurary=(outputs.argmax(1)==targets).sum()
total_accurary=total_accurary+accurary
total_test_step=total_test_step+1
print("测试集上的loss:{}".format(total_test_loss))
print("测试集上的accurary:{}".format(total_accurary/test_data_size))
writer.add_scalar("test_loss", total_test_loss, total_test_step)
writer.add_scalar("test_accurary", total_accurary/test_data_size, total_test_step)
torch.save(mynet,"mynet_{}.pth".format(i))
writer.close()
效果