用Colab进行Cifar10图像分类

用Colab进行Cifar10图像分类

---

```python
import torch
import torchvision
from torch.utils.tensorboard import SummaryWriter
from torch import nn
from torch.utils.data import DataLoader
dataset_transform=torchvision.transforms.Compose([
    torchvision.transforms.Resize((32,32)),
    torchvision.transforms.ToTensor(),
    torchvision.transforms.Normalize((0.485,0.456,0.406),(0.229,0.224,0.225))
])

train_data=torchvision.datasets.CIFAR10(root="../data",train=True,transform=dataset_transform,download=True)
test_data=torchvision.datasets.CIFAR10(root="../data",train=False,transform=dataset_transform,download=True)

train_dataloader=DataLoader(train_data,batch_size=64)
test_dataloader=DataLoader(test_data,batch_size=64)
test_data_size=len(test_data)

class Cifar10(nn.Module):
    def __init__ (self):
        super(Cifar10,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
Cifar=Cifar10()
if torch.cuda.is_available():
    Cifar=Cifar.cuda()

loss_fn=nn.CrossEntropyLoss()
if torch.cuda.is_available():
    loss_fn=loss_fn.cuda()

learning_rate=0.01
optimizer=torch.optim.SGD(Cifar.parameters(),lr=learning_rate)

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("../logs_train")
%load_ext tensorboard

for i in range(epoch):
    print("-------第 {} 轮训练开始-------".format(i+1))

    # 训练步骤开始
    Cifar.train()
    for data in train_dataloader:
        imgs, targets = data
        if torch.cuda.is_available():
            imgs = imgs.cuda()
            targets = targets.cuda()
        outputs = Cifar(imgs)
        loss = loss_fn(outputs, targets)

        # 优化器优化模型
        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)

    # 测试步骤开始
    Cifar.eval()
    total_test_loss = 0
    total_accuracy = 0
    with torch.no_grad():
        for data in test_dataloader:
            imgs, targets = data
            if torch.cuda.is_available():
                imgs = imgs.cuda()
                targets = targets.cuda()
            outputs = Cifar(imgs)
            loss = loss_fn(outputs, targets)
            total_test_loss = total_test_loss + loss.item()
            accuracy = (outputs.argmax(1) == targets).sum()
            total_accuracy = total_accuracy + accuracy

    print("整体测试集上的Loss: {}".format(total_test_loss))
    print("整体测试集上的正确率: {}".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 = total_test_step + 1

    torch.save(Cifar, "Cifar1_{}.pth".format(i))
    print("模型已保存")

writer.close()

在colab上打开tensorboard可视化功能需要命令如下：

!pip install tensorboard
!pip install tensorboardx
!pip install tensorflow

随后创建SummerWriter实例后
%load_ext tensorboard命令启动功能

%tensorboard --logdir …/logs_train打开