Is MB v2 code complete?

[lcmeng]

Hi,

In reference to issue #36, according to the README:

After searching is done, the top1 encoding vector will be shown in the log. By simply copying the encoding vector to the rngs = [ ] in evaluate.py, you can evaluate the Pruned Network corresponding to this encoding vector.

I did a quick search and found that rngs is only used in MB v1 eval. The MB v2 search log contains the top 50 results for each iteration. So the first questions is: which part of the log should be copied? Is it the No.1 array generated by the last iteration?

The second question is that MB v2 channel config code seems to be different than MB v1's, can you please provide the steps or a patch that will get MB v2 eval to work?