以下是一个比较PyTorch和Keras在CIFAR-10数据集上的示例。

首先，我们从PyTorch开始。

PyTorch示例代码：

import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torchvision import datasets, transforms

# 定义模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 64, 5)
        self.conv2 = nn.Conv2d(64, 128, 5)
        self.fc1 = nn.Linear(128*5*5, 256)
        self.fc2 = nn.Linear(256, 10)

    def forward(self, x):
        x = F.relu(self.conv1(x))
        x = F.max_pool2d(x, 2)
        x = F.relu(self.conv2(x))
        x = F.max_pool2d(x, 2)
        x = x.view(-1, 128*5*5)
        x = F.relu(self.fc1(x))
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)

# 加载和预处理CIFAR-10数据集
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

train_set = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
test_set = datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)

train_loader = torch.utils.data.DataLoader(train_set, batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(test_set, batch_size=64, shuffle=False)

# 定义模型、优化器和损失函数
model = Net()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.9)
criterion = nn.CrossEntropyLoss()

# 训练模型
model.train()
for epoch in range(10):
    for batch_idx, (data, target) in enumerate(train_loader):
        optimizer.zero_grad()
        output = model(data)
        loss = criterion(output, target)
        loss.backward()
        optimizer.step()

# 在测试集上评估模型
model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
    for data, target in test_loader:
        output = model(data)
        test_loss += criterion(output, target).item()
        pred = output.argmax(dim=1, keepdim=True)
        correct += pred.eq(target.view_as(pred)).sum().item()

test_loss /= len(test_loader.dataset)
accuracy = 100. * correct / len(test_loader.dataset)

print(f'Test Loss: {test_loss:.4f}, Accuracy: {accuracy:.2f}%')

接下来，我们看一下如何在Keras中实现相同的功能。

Keras示例代码：

import keras
from keras.datasets import cifar10
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Flatten, Dense
from keras.optimizers import SGD
from keras.losses import SparseCategoricalCrossentropy

# 加载和预处理CIFAR-10数据集
(x_train, y_train), (x_test, y_test) = cifar10.load_data()
x_train = x_train.astype('float32') / 255.0
x_test = x_test.astype('float32') / 255.0

# 定义模型
model = Sequential()
model.add(Conv2D(64, (5, 5), activation='relu', input_shape=(32, 32, 3)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(128, (5, 5), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dense(10, activation='softmax'))

# 定义优化器和损失函数
optimizer = SGD(lr=0.01, momentum=0.9)
criterion = SparseCategoricalCrossentropy()

# 编译和训练模型
model.compile(optimizer=optimizer, loss=criterion, metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=64, epochs=10, verbose=1)

# 在测试集上评估模型
test_loss, accuracy