采用卷积神经网络(CNN)进行MNIST数据集分类

MNIST数据集是一个手写数字图像集合，其中包含60,000个训练示例和10,000个测试示例。每个图像都是28x28像素的灰度图像。在本文中，我们将使用卷积神经网络(CNN)来对MNIST数据集进行分类。

首先，我们需要导入需要的库：

import tensorflow as tf
from tensorflow.keras import datasets, layers, models
import matplotlib.pyplot as plt

接下来，我们将加载MNIST数据集，并将其分为训练集和测试集：

(train_images, train_labels), (test_images, test_labels) = datasets.mnist.load_data()

我们可以使用Matplotlib库来查看一些训练图像：

plt.figure()
plt.imshow(train_images[0])
plt.colorbar()
plt.grid(False)
plt.show()

然后，我们需要对图像进行预处理，将像素值缩小到0到1之间，并将其转换为四维张量，以便将其输入到CNN模型中：

train_images = train_images / 255.0
test_images = test_images / 255.0

train_images = train_images.reshape((60000, 28, 28, 1))
test_images = test_images.reshape((10000, 28, 28, 1))

接下来，我们将构建CNN模型。我们将使用两个卷积层和两个池化层，然后将图像输入到全连接层中：

model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10))

最后，我们将编译模型并训练它：

model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

history = model.fit(train_images, train_labels, epochs=10, 
                    validation_data=(test_images, test_labels))

训练完成后，我们可以使用测试集来评估模型的性能：

test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)

print('\nTest accuracy:', test_acc)

完整代码：

import tensorflow as tf
from tensorflow.keras import datasets, layers, models
import matplotlib.pyplot as plt

# load the dataset
(train_images, train_labels), (test_images, test_labels) = datasets.mnist.load_data()

# preprocess the data
train_images = train_images / 255.0
test_images = test_images / 255.0

train_images = train_images.reshape((60000, 28, 28, 1))
test_images = test_images.reshape((10000, 28, 28, 1))

# build the model
model = models.Sequential()
model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(64, activation='relu'))
model.add(layers.Dense(10))

# compile the model
model.compile(optimizer='adam',
              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
              metrics=['accuracy'])

# train the model
history = model.fit(train_images, train_labels, epochs=10, 
                    validation_data=(test_images, test_labels))

# evaluate the model
test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2)

print('\nTest accuracy:', test_acc)

# plot the accuracy and loss curves
acc = history.history['accuracy']
val_acc = history.history['val_accuracy']
loss = history.history['loss']
val_loss = history.history['val_loss']

epochs_range = range(10)

plt.figure(figsize=(8, 8))
plt.subplot(2, 2, 1)
plt.plot(epochs_range, acc, label='Training Accuracy')
plt.plot(epochs_range, val_acc, label='Validation Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')

plt.subplot(2, 2, 2)
plt.plot(epochs_range, loss, label='Training Loss')
plt.plot(epochs_range, val_loss, label='Validation Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()