TensorFlow Attempting to use uninitialized value in variable initialization

Question

I am trying to implement multivariate linear regression in Python using TensorFlow  but have run into some logical and implementation issues  My code throws the following error   Attempting to use uninitialized value Variable Caused by op u Variable read    Ideally the weights output should be  2  3   def hypothesis function input 2d matrix trainingexamples                          output matrix of trainingexamples                          initial parameters of hypothesis function                          learning rate  num steps         calculate num attributes and num examples     number of attributes   len input 2d matrix trainingexamples 0       number of trainingexamples   len input 2d matrix trainingexamples        Graph inputs     x          for i in range 0  number of attributes  1           x append tf placeholder  float        y input   tf placeholder  float          Create Model and Set Model weights     parameters          for i in range 0  number of attributes  1           parameters append              tf Variable initial parameters of hypothesis function i          Contruct linear model     y   tf Variable parameters 0    float       for i in range 1  number of attributes  1           y   tf add y  tf multiply x i   parameters i           Minimize the mean squared errors     loss   tf reduce mean tf square y - y input       optimizer   tf train GradientDescentOptimizer learning rate      train   optimizer minimize loss        Initialize the variables     init   tf initialize all variables          launch the graph     session   tf Session       session run init      for step in range 1  num steps   1  1           for i in range 0  number of trainingexamples  1               feed                  for j in range 0  number of attributes  1                   array    input 2d matrix trainingexamples i  j                   feed j    array             array1    output matrix of trainingexamples i               feed number of attributes    array1             session run train  feed dict feed       for i in range 0  number of attributes - 1  1           print  session run parameters i     array     0 0  1 0  2 0    0 0  2 0  3 0    0 0  4 0  5 0   hypothesis function array   8 0  13 0  23 0    1 0  1 0  1 0   0 01  200

User · Answer

Normally there are two ways of initializing variables, 1) using the sess.run(tf.global_variables_initializer()) as the previous answers noted; 2) the load the graph from checkpoint.

You can do like this:

sess = tf.Session(config=config)
saver = tf.train.Saver(max_to_keep=3)
try:
    saver.restore(sess, tf.train.latest_checkpoint(FLAGS.model_dir))
    # start from the latest checkpoint, the sess will be initialized 
    # by the variables in the latest checkpoint
except ValueError:
    # train from scratch
    init = tf.global_variables_initializer()
    sess.run(init)

And the third method is to use the tf.train.Supervisor. The session will be

Create a session on 'master', recovering or initializing the model as needed, or wait for a session to be ready.

sv = tf.train.Supervisor([parameters])
sess = sv.prepare_or_wait_for_session()

User · Answer

It s not 100  clear from the code example  but if the list initial parameters of hypothesis function is a list of tf Variable objects  then the line session run init  will fail because TensorFlow isn t  yet  smart enough to figure out the dependencies in variable initialization  To work around this  you should change the loop that creates parameters to use initial parameters of hypothesis function i  initialized value    which adds the necessary dependency   parameters      for i in range 0  number of attributes  1       parameters append tf Variable          initial parameters of hypothesis function i  initialized value

User · Answer

There is another the error happening which related to the order when calling initializing global variables  I ve had the sample of code has similar error FailedPreconditionError  see above for traceback   Attempting to use uninitialized value W  def linear X  n input  n output  activation   None       W   tf Variable tf random normal  n input  n output   stddev 0 1   name  W       b   tf Variable tf constant 0  dtype tf float32  shape  n output    name  b       if activation    None          h   tf nn tanh tf add tf matmul X  W  b   name  h       else          h   tf add tf matmul X  W  b  name  h       return h  from tensorflow python framework import ops ops reset default graph   g   tf get default graph   print  op name for op in g get operations     with tf Session   as sess        RUN INIT     sess run tf global variables initializer          But W hasn t in the graph yet so not know to initialize        EVAL then error     print linear np array   1 0 2 0 3 0    astype np float32   3  3  eval      You should change to following  from tensorflow python framework import ops ops reset default graph   g   tf get default graph   print  op name for op in g get operations     with tf Session   as        NOT RUNNING BUT ASSIGN     l   linear np array   1 0 2 0 3 0    astype np float32   3  3        RUN INIT     sess run tf global variables initializer        print  op name for op in g get operations           ONLY EVAL AFTER INIT     print l eval session sess

User · Answer

Run this   init   tf global variables initializer   sess run init    Or  depending on the version of TF that you have    init   tf initialize all variables   sess run init

User · Answer

I want to give my resolution  it work when i replace the line  session   tf Session    with  sess   tf InteractiveSession     Hope this will be useful to others

User · Answer

run both    sess run tf global variables initializer     sess run tf local variables initializer

[python] TensorFlow: "Attempting to use uninitialized value" in variable initialization

Examples related to python

Examples related to machine-learning

Examples related to linear-regression

Examples related to tensorflow