Organizing transfer learning

Basically I organized the keyword arguments for the input networks used in the estimator.

Now, we can expect that the network has this function signature: inputs, reuse=False, is_training_mode = True, trainable_variables=True

where,

• reuse: If you want to reuse the tensorflow variables
• is_training_mode: If you are in training mode or not.
• trainable_variables: IF the set of variables in the network function are trainable

Tests are passing.