CODEWITHSUNDEEP
tensorflow
Talha Yousuf
Talha Yousuf

Reputation: 301

Why the variables inside function are not initialized?

Produced below is an excerpt from my code: enter image description here

And then I run this: enter image description here

and I get this error despite the fact that I even tried tf.initialize_all_variables() enter image description here

Can I know, WHY THE VARIABLES INSIDE FUNCTION [linear_layer] ARE NOT INITIALIZED?

Upvotes: 0

Views: 70

Answers (1)

zihaozhihao
zihaozhihao

Reputation: 4495

You should explicitly create the variable such as out to let tensorflow know which graph element is evaluated. In your original code, you haven't built the graph when you call tf.global_variables_initializer(). That's why W is not initialized. 

def linear_layer(input, units):
    W = tf.Variable(initial_value=glorot(shape=(input.get_shape().as_list()[1], units)), name="W")
    B = tf.Variable(initial_value=tf.zeros(shape=(input.get_shape().as_list()[0], 1)), name="B")
    out = tf.matmul(input, W) + B
    return out

out = linear_layer(input=tf.constant([[1.,2.,3.],[4.,5.,6.]]), units=10)

with tf.Session() as sess:
    sess.run(tf.global_variables_initializer())
    sess.run(tf.local_variables_initializer())
    print(sess.run(out))

# [[ 0.8285629   0.7860288   1.8736962   0.4321289  -0.9692887  -1.638855
#   -0.19338632  0.5580156  -0.13394058  1.6745124 ]
#  [ 1.9110355   1.2211521   3.2454844  -0.9029484  -2.0184612  -2.753471
#   -0.29346204  0.340119    0.04118478  2.893313  ]]

Upvotes: 1

Related Questions