选“SAME”时，一来减缓图像变小的速度，二来防止边界信息丢失

# 导入模块
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torchvision
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
import matplotlib.pyplot as plt

导入报错没有啥就pip install 啥

# 数据下载并进行标准化
transform = transforms.Compose([transforms.ToTensor(),transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = DataLoader(trainset, batch_size=4, shuffle=True, num_workers=0)
test_set = torchvision.datasets.CIFAR10(root='./data', train=False, download=False, transform=transform)
testloader = DataLoader(test_set, batch_size=4, shuffle=False, num_workers=0)
 
classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
 
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

context.set_context(mode=context.GRAPH_MODE, device_target="GPU")

# 创建卷积神经网络
class CNN(nn.Module):
    def __init__(self):
        super(CNN, self).__init__()
        self.conv1 = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=5, stride=1)
        self.pool1 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.conv2 = nn.Conv2d(in_channels=16, out_channels=36, kernel_size=3, stride=1)
        self.pool2 = nn.MaxPool2d(kernel_size=2, stride=2)
        self.fc1 = nn.Linear(1296, 128)
        self.fc2 = nn.Linear(128, 10)
 
    def forward(self, x):
        x = self.pool1(F.relu(self.conv1(x)))
        x = self.pool2(F.relu(self.conv2(x)))
        # print(x.shape)
        x = x.view(-1, 36 * 6 * 6)
        x = F.relu(self.fc2(F.relu(self.fc1(x))))
        return x

    net = CNN()
    net = net.to(device)

# 训练模型
# 选择优化器
import torch.optim as optim

# 创建优化器
criterion = nn.CrossEntropyLoss()

# 初始化优化器，同时设置学习率和冲量
optimizer = optim.SGD(net.parameters(), lr=0.0001, momentum=0.7) 
 
for epoch in range(10):
    running_loss = 0
    for i, data in enumerate(trainloader, 0):
        # 输入训练数据
        inputs, labels = data
        inputs, labels = inputs.to(device), labels.to(device)
 
        # 设置权重梯度相消
        optimizer.zero_grad()
 
        # 正向和反向传播
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
 
        # 显示损失值
        running_loss += loss.item()
        if i % 2000 == 1999:  #显示每2000个样例的损失值
            print('[%d,%5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0
print("Finished Training")
 
# 预测模型
correct = 0
tatal = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        images, labels = images.to(device), labels.to(device)
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        tatal += labels.size(0)
        correct += (predicted == labels).sum().item()
print('Accuracy of our CNN_Net is : %d %%' % (100 * correct / tatal))