tf环境下，VGG16训练mnist，并达到一个很高的准确率，给出完整代码，打印运算结果，打印运行时间 并可视化

以下是在 TensorFlow 环境下，使用 VGG16 模型训练 MNIST 数据集并可视化的完整代码：

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

# 加载数据集
(train_images, train_labels), (test_images, test_labels) = datasets.mnist.load_data()

# 数据预处理
train_images = train_images.reshape((60000, 28, 28, 1))
test_images = test_images.reshape((10000, 28, 28, 1))
train_images, test_images = train_images / 255.0, test_images / 255.0

# 构建 VGG16 模型
model = models.Sequential()
model.add(layers.Conv2D(64, (3, 3), activation='relu', input_shape=(28, 28, 1)))
model.add(layers.Conv2D(64, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.Conv2D(128, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(256, (3, 3), activation='relu'))
model.add(layers.Conv2D(256, (3, 3), activation='relu'))
model.add(layers.Conv2D(256, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(512, (3, 3), activation='relu'))
model.add(layers.Conv2D(512, (3, 3), activation='relu'))
model.add(layers.Conv2D(512, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Conv2D(512, (3, 3), activation='relu'))
model.add(layers.Conv2D(512, (3, 3), activation='relu'))
model.add(layers.Conv2D(512, (3, 3), activation='relu'))
model.add(layers.MaxPooling2D((2, 2)))
model.add(layers.Flatten())
model.add(layers.Dense(4096, activation='relu'))
model.add(layers.Dense(4096, activation='relu'))
model.add(layers.Dense(10, activation='softmax'))

# 编译模型
model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# 训练模型
start_time = time.time()
history = model.fit(train_images, train_labels, epochs=10, 
                    validation_data=(test_images, test_labels))
end_time = time.time()

# 打印运算结果
print(f"Train accuracy: {history.history['accuracy'][-1]}")
print(f"Test accuracy: {history.history['val_accuracy'][-1]}")
print(f"Total time: {end_time - start_time:.2f} seconds")

# 可视化训练过程
plt.plot(history.history['accuracy'], label='train accuracy')
plt.plot(history.history['val_accuracy'], label='test accuracy')
plt.title('Training and Testing Accuracy')
plt.xlabel('Epoch')
plt.ylabel('Accuracy')
plt.legend()
plt.show()

在运行完上述代码后，程序将会输出训练过程中的准确率、测试准确率和运行时间，并且会显示训练和测试准确率的可视化图表。