Probably a wrong mean in autoencoder example?

Hi, 
I just wanted to ensure that the mean subtraction in the Convolution Autoencoder's test images are correct. [Here](https://github.com/pkmital/tensorflow_tutorials/blob/master/python/09_convolutional_autoencoder.py#L157 ) the mean of the train image is being subtracted from the test images. Correct me if I am wrong, else i'd open a pull request to fix this :)

Cheers,
Ramana