Update faq.md to show how to assign num_readers (#7645)

research/deeplab/g3doc/faq.md

@@ -68,7 +68,7 @@ image dimension is all equal to 1024x2048.
 ___
 Q9: Why multi-gpu training is slow?
 
-A: Please try to use more threads to pre-process the inputs. For, example change [num_readers = 4](https://github.com/tensorflow/models/blob/master/research/deeplab/utils/input_generator.py#L71) and [num_threads = 4](https://github.com/tensorflow/models/blob/master/research/deeplab/utils/input_generator.py#L72).
+A: Please try to use more threads to pre-process the inputs. For, example change [num_readers = 4](https://github.com/tensorflow/models/blob/master/research/deeplab/train.py#L457).
 ___