第五章（5.5节）最佳实践样例中的mnist_eval.py运行后输出一直是After 29001 training step(s)...是怎么回事？

[dhwgithub]

按mnist_eval.py样例运行给出的代码实际输出结果：

After 29001 training step(s), validation accuracy = 0.9852
After 29001 training step(s), validation accuracy = 0.9852
After 29001 training step(s), validation accuracy = 0.9852
......

应该输出的结果是：

INFO:tensorflow:Restoring parameters from MNIST_model/mnist_model-4001
After 4001 training step(s), validation accuracy = 0.9826
INFO:tensorflow:Restoring parameters from MNIST_model/mnist_model-5001
After 5001 training step(s), validation accuracy = 0.983
INFO:tensorflow:Restoring parameters from MNIST_model/mnist_model-6001
After 6001 training step(s), validation accuracy = 0.9832
......
After 29001 training step(s), validation accuracy = 0.9856

我用的是tensorflow1.5+python3.5版本
这是什么原因？应该怎么改