如何生成正确的MNIST镜像？

import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data

# 加载MNIST数据集
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)

# 创建一个新的TensorFlow图
graph = tf.Graph()

with graph.as_default():
    # 定义输入和输出的占位符
    x = tf.placeholder(tf.float32, [None, 784])
    y = tf.placeholder(tf.float32, [None, 10])

    # 定义模型结构
    W = tf.Variable(tf.zeros([784, 10]))
    b = tf.Variable(tf.zeros([10]))
    logits = tf.matmul(x, W) + b
    predictions = tf.nn.softmax(logits)

    # 定义损失函数和优化器
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=logits))
    optimizer = tf.train.GradientDescentOptimizer(learning_rate=0.5).minimize(loss)

    # 定义准确率评估指标
    correct_predictions = tf.equal(tf.argmax(predictions, 1), tf.argmax(y, 1))
    accuracy = tf.reduce_mean(tf.cast(correct_predictions, tf.float32))

    # 初始化变量
    init = tf.global_variables_initializer()

# 创建一个会话并运行图
with tf.Session(graph=graph) as sess:
    sess.run(init)

    # 训练模型
    for i in range(1000):
        batch_xs, batch_ys = mnist.train.next_batch(100)
        sess.run(optimizer, feed_dict={x: batch_xs, y: batch_ys})

    # 在测试集上评估模型
    test_accuracy = sess.run(accuracy, feed_dict={x: mnist.test.images, y: mnist.test.labels})
    print("Test Accuracy: {:.2f}%".format(test_accuracy * 100))