Alexnet implementation in tensorflow has incomplete architecture where 2 convolution neural layers are missing. This issue is in reference to the python notebook mentioned below.

https://github.com/donnemartin/data-science-ipython-notebooks/blob/master/deep-learning/tensor-flow-examples/notebooks/3_neural_networks/alexnet.ipynb

• This item located in 2.3. 常用设置 and 2.3. Common settings.It would an effect to cause chinese user confused.Please update it.

![image](https://user-images.githubusercontent.com/26212551/68575

The documentation file appears to have been generated with no space between the hashes and the header text. This is causing the headers to not display correctly, and is difficult to read. See below for an example of with and without the space:

##

Mobius API Documentation

As outlined in #16, it's often useful to extend fine-grained control of sharding to the user. It can be solved by wrapping integers with an identity hash function, but that seems less than ideal. It might be useful to provide this functionality as part of bigslice.Reshuffle.