如何在完整的验证示例中评估Tensorflow模型

import tensorflow as tf
from tensorflow import keras

# 加载MNIST数据集
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()

# 对训练集和测试集进行归一化处理
x_train = x_train / 255.0
x_test = x_test / 255.0

# 定义模型
model = keras.Sequential([
    keras.layers.Flatten(input_shape=(28, 28)),
    keras.layers.Dense(128, activation='relu'),
    keras.layers.Dense(10, activation='softmax')
])

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

# 训练模型
model.fit(x_train, y_train, epochs=5)

# 测试模型
test_loss, test_acc = model.evaluate(x_test, y_test)
print('Test accuracy:', test_acc)

# 验证模型
predictions = model.predict(x_test)
print(predictions[0])
print(y_test[0])