The key is to understand the difference between variables and other tensors in the graph. Any newly created tensors will gain a prefix from a name scope. tf.get_variable will look for existing variables without the name scope modifier. Newly created variables with tf.get_variable will still get their name's augmented.
The script below highlights these differences. The intention is to reproduce the simple function by refactoring the tf.matmul(x, A) + b line and variable creation into a separate function add_layer.
import tensorflow as tf
def get_x():
return tf.constant([[1., 2., 3.]], dtype=tf.float32)
def report(out1, out2):
print(out1.name)
print(out2.name)
variables = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES)
print([v.name for v in variables])
def simple():
A = tf.get_variable(shape=(3, 3), dtype=tf.float32, name='A')
b = tf.get_variable(shape=(3,), dtype=tf.float32, name='b')
x = get_x()
out1 = tf.matmul(x, A) + b
out2 = tf.matmul(out1, A) + b
return out1, out2
def add_layer(x):
A = tf.get_variable(shape=(3, 3), dtype=tf.float32, name='A')
b = tf.get_variable(shape=(3,), dtype=tf.float32, name='b')
return tf.matmul(x, A) + b
def no_scoping():
x = get_x()
out1 = add_layer(x)
out2 = add_layer(out1)
return out1, out2
def different_name_scopes():
x = get_x()
with tf.name_scope('first_layer'):
out1 = add_layer(x)
with tf.name_scope('second_layer'):
out2 = add_layer(out1)
return out1, out2
def same_name_scope():
x = get_x()
with tf.name_scope('first_layer'):
out1 = add_layer(x)
with tf.name_scope('first_layer'):
out2 = add_layer(out1)
return out1, out2
def different_variable_scopes():
x = get_x()
with tf.variable_scope('first_layer'):
out1 = add_layer(x)
with tf.variable_scope('second_layer'):
out2 = add_layer(out1)
return out1, out2
def same_variable_scope():
x = get_x()
with tf.variable_scope('first_layer'):
out1 = add_layer(x)
with tf.variable_scope('first_layer'):
out2 = add_layer(out1)
return out1, out2
def same_variable_scope_reuse():
x = get_x()
with tf.variable_scope('first_layer'):
out1 = add_layer(x)
with tf.variable_scope('first_layer', reuse=True):
out2 = add_layer(out1)
return out1, out2
def test_fn(fn, name):
graph = tf.Graph()
with graph.as_default():
try:
print('****************')
print(name)
print('****************')
out1, out2 = fn()
report(out1, out2)
print('----------------')
print('SUCCESS')
print('----------------')
except Exception:
print('----------------')
print('FAILED')
print('----------------')
for fn, name in [
[simple, 'simple'],
[no_scoping, 'no_scoping'],
[different_name_scopes, 'different_name_scopes'],
[same_name_scope, 'same_name_scope'],
[different_variable_scopes, 'different_variable_scopes'],
[same_variable_scope, 'same_variable_scope'],
[same_variable_scope_reuse, 'same_variable_scope_reuse']
]:
test_fn(fn, name)
Results:
****************
simple
****************
add:0
add_1:0
[u'A:0', u'b:0']
----------------
SUCCESS
----------------
****************
no_scoping
****************
----------------
FAILED
----------------
****************
different_name_scopes
****************
----------------
FAILED
----------------
****************
same_name_scope
****************
----------------
FAILED
----------------
****************
different_variable_scopes
****************
first_layer/add:0
second_layer/add:0
[u'first_layer/A:0', u'first_layer/b:0', u'second_layer/A:0', u'second_layer/b:0']
----------------
SUCCESS
----------------
****************
same_variable_scope
****************
----------------
FAILED
----------------
****************
same_variable_scope_reuse
****************
first_layer/add:0
first_layer_1/add:0
[u'first_layer/A:0', u'first_layer/b:0']
----------------
SUCCESS
----------------
Note that using different variable_scopes without reuse doesn't raise an error, but creates multiple copies of A and b, which may not be intended.
