Parallel Processing

[jswilson]

First, an enormous thank you such a great project; your work is really excellent!

I had a question about train2 and parallelizing the processing. I had been running on a single GPU, but I tried a 16-GPU system and didn't notice a performance improvement. I added log_device_placement=True to see what steps were being assigned to which GPU, and it looks like everything goes to GPU:0. I am kind of new to Tensorflow; is it the case that this will currently only use one GPU as written? Thank you!