Gan

Ok, so I think that the modifications I made here can be merged ...

Two main changes as compared to the master:

1. Added some layers
2. Modified the way variable name and scope is handled in layers (and in SequenceNetwork as well)

Change 1 should by no means affect what has been done until now (on the master). However, change 2 may require a bit of adaptation, especially when defining architectures and layers ...

@tiago.pereira I'll let you check and then we can discuss

Also, I think that this will be irrelevant when we'll go to tf-slim anyway !

bob/learn/tensorflow/datashuffler/Disk.py

@@ -150,7 +150,7 @@ class Disk(Base):
       if len(self.indexes) < self.batch_size:
 
         print "should add examples to the current minibatch {0}".format(len(self.indexes))
-        # since we reached the end of an epoch, we'll hace to reconsider all the data
+        # since we reached the end of an epoch, we'll have to reconsider all the data
         epoch_done = True
         number_of_examples_to_add = self.batch_size - len(self.indexes) 
         added_examples = 0