Exclude specific tensors being updated by optimizer in TensorFlow

Question

I have two graphs, which I suppose to train them independently, which means I have two different optimizers, but at the same time one of them is using the tensor values of the other graph. As a result, I need to be able to stop specific tensors being updated while training one of the graphs. I have assigned two different namescopes two my tensors and using this code to control updates over tensors for different optimizers:

mentor_training_vars = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, "mentor")
train_op_mentor = mnist.training(loss_mentor, FLAGS.learning_rate, mentor_training_vars)
mentee_training_vars = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, "mentee")
train_op_mentee = mnist.training(loss_mentee, FLAGS.learning_rate, mentee_training_vars)

the vars variable is being used like below, in the training method of mnist object:

def training(loss, learning_rate, var_list):

  # Add a scalar summary for the snapshot loss.
  tf.summary.scalar('loss', loss)
  # Create the gradient descent optimizer with the given learning rate.
  optimizer = tf.train.GradientDescentOptimizer(learning_rate)
  # Create a variable to track the global step.
  global_step = tf.Variable(0, name='global_step', trainable=False)
  # Use the optimizer to apply the gradients that minimize the loss
  # (and also increment the global step counter) as a single training step.
  train_op = optimizer.minimize(loss, global_step=global_step, var_list=var_list)
  return train_op

I'm using the var_list attribute of the optimizer class in order to control vars being updated by the optimizer.

Right now I'm confused whether I have done what I supposed to do appropriately, and even if there is anyway to check if any optimizer would only update partial of a graph?

I would appreciate if anyone can help me with this issue.

Thanks!

I'm not sure there's an easy way, but you could record the value after some iterations and check if it changed. — drpng, Feb 14 '17 at 07:27

score 1 · Answer 1 · answered Feb 14 '17 at 10:09

I have had a similar problem and used the same approach as you, i.e. via the var_list argument of the optimizer. I then checked whether the variables not intended for training stayed the same using:

the_var_np = sess.run(tf.get_default_graph().get_tensor_by_name('the_var:0'))
assert np.equal(the_var_np, pretrained_weights['the_var']).all()

pretrained_weights is a dictionary returned by np.load('some_file.npz') which I used to store the pre-trained weights to disk.

Just in case you need that as well, here is how you can override a tensor with a given value:

value = pretrained_weights['the_var']
variable = tf.get_default_graph().get_tensor_by_name('the_var:0')
sess.run(tf.assign(variable, value))

Exclude specific tensors being updated by optimizer in TensorFlow

1 Answers1