Tensorflow variable scope: reuse if variable exists

Question

I want a piece of code that creates a variable within a scope if it doesn\'t exist, and access the variable if it already exists. I need it to be the same c

Answer 1

We can write our abstraction over tf.varaible_scope than uses reuse=None on the first call and uses reuse=True on the consequent calls:

def variable_scope(name_or_scope, *args, **kwargs):
  if isinstance(name_or_scope, str):
    scope_name = tf.get_variable_scope().name + '/' + name_or_scope
  elif isinstance(name_or_scope, tf.Variable):
    scope_name = name_or_scope.name

  if scope_name in variable_scope.scopes:
    kwargs['reuse'] = True
  else:
    variable_scope.scopes.add(scope_name)

  return tf.variable_scope(name_or_scope, *args, **kwargs)
variable_scope.scopes = set()

Usage:

with variable_scope("foo"): #create the first time
    v = tf.get_variable("v", [1])

with variable_scope("foo"): #reuse the second time
    v = tf.get_variable("v", [1])