CODEWITHSUNDEEP
pythontensorflow
Nimitz14
Nimitz14

Reputation: 2358

Tensorflow: How to give variables scope

I have to first pretrain a network before training it. I do this using code in separate files with their own sessions, but the variables from the first session are still getting carried over and causing problems (as I'm running both these files within one 'main' file).

I could get around this problem by simply running my pretrain file which saves the trained layers and then running my training file which loads the saved layers in. But it would be nice to be able to do these two things in one step. How can I 'break the link' and avoid unwanted variables having a global scope?

The 'main' file looks something like this:

from util import pretrain_nn
from NN import Network

shape = [...]
layer_save_file = ''
data = get_data()

# Trains and saves layers
pretrain_nn(shape, data, layer_save_file) 

# If I were to print all variables (using tf.all_variables) 
# variables only used in pretrain_nn show up 
# (the printing would be done inside `Network`)
NN = Network(shape, pretrain=True, layer_save_file) 

NN.train(data)

# Doesn't work because apparently some variables haven't been initialized.
NN.save()

Upvotes: 1

Views: 490

Answers (1)

mrry
mrry

Reputation: 126184

The variables' lifetime is implicitly tied to the TensorFlow graph, and by default both of your computations will be added to the same (global) graph. You can scope them appropriately using with tf.Graph().as_default(): blocks around each of the subcomputations:

with tf.Graph().as_default():
  # Trains and saves layers
  pretrain_nn(shape, data, layer_save_file) 

with tf.Graph().as_default():
  NN = Network(shape, pretrain=True, layer_save_file) 

  NN.train(data)

  NN.save()

Upvotes: 1

Related Questions