Fix python3 batch_iter or use tensorflow data batchsize generator

[SrMouraSilva]

utils.py Line 37

# Use // instead /
n_batches = N / batch_size + (N % batch_size > 0)

Python 2: float / int -> int
Python 3: float / int -> float
Python 3: float // int -> int

use tensorflow data batchsize generator

I will add information later

[yell]

Thanks for spotting.
If you find more bugs please add info or perhaps open a PR.
I actually plan to rewrite many things better when I have a bit more spare time, and also to rigorously check python3-compatibility etc.

[SrMouraSilva]

Hello, Yelysei Bondarenko

I'm working with RBM in master degree. My current implementation in tensorflow might have some problems. I was testing on yours.

There is the possibility that I migrate to your implementation. But I need to work with RBMCF and Conditional RBM. I'm not sure how to do it properly.

Anyway, I will do to make this merge request :D

---

A question. How to?

configure metrics to display during learning (which ones, frequency, format etc.)

[yell]

Please have a look here: https://github.com/monsta-hd/boltzmann-machines/blob/master/boltzmann_machines/rbm/base_rbm.py#L53-L72