Remove <center> tags, which are breaking images in README.md files

Author: nealwu

inception/README.md

@@ -18,9 +18,7 @@ evaluation with a computational cost of 5 billion multiply-adds per inference
 and with using less than 25 million parameters. Below is a visualization of the
 model architecture.
 
-<center>
 ![Inception-v3 Architecture](g3doc/inception_v3_architecture.png)
-</center>
 
 ## Description of Code
 

street/README.md

@@ -32,11 +32,9 @@ identify the name of a street (in France) from an image containing upto four
 different views of the street name sign. The model merges information from the
 different views and normalizes the text to the correct format. For example:
 
-<center>
 ![Example image](g3doc/avdessapins.png)
 
 Avenue des Sapins
-</center>
 
 
 ## Installing and setting up the STREET model