Weight Normalization

[antonilo]

Usually during training add a normalization to the weights used in CNN is a good way to improve the generalization performance.
If I did not misread the code, at the moment it seems that it is not trivial to get the weights during learning.
It seems to me that it might be a good idea to store also the weights in the Network class for easy retrieval during learning.

[ethereon]

The weights and biases are stored in regular tensorflow variables (see the load function for instance). You can access these just like any other tensorflow variables (which you can also use for adding regularization). For more details, see here.