TensorFlow: “Attempting to use uninitialized value” in variable initialization

Question

Here's my code.

import tensorflow as tf

a=tf.Variable(tf.constant([0,1,2],dtype=tf.int32))
b=tf.Variable(tf.constant([1,1,1],dtype=tf.int32))
recall=tf.metrics.recall(b,a)

init=tf.global_variables_initializer()
with tf.Session() as sess:
    sess.run(init)
    rec=sess.run(recall)
    print(rec)

I tried to test tf.metrics.precision and got the following error message.

FailedPreconditionError (see above for traceback): Attempting to use uninitialized value recall/true_positives/count
     [[Node: recall/true_positives/count/read = Identity[T=DT_FLOAT, _class=["loc:@recall/true_positives/count"], _device="/job:localhost/replica:0/task:0/gpu:0"](recall/true_positives/count)]]
     [[Node: recall/value/_15 = _Recv[client_terminated=false, recv_device="/job:localhost/replica:0/task:0/cpu:0", send_device="/job:localhost/replica:0/task:0/gpu:0", send_device_incarnation=1, tensor_name="edge_73_recall/value", tensor_type=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"]()]]

Welcome to SO! Please don't add screenshots of code or errors. Please take some time to read help pages, especially sections "What topics can I ask about here?" and "What types of questions should I avoid asking?". Also please take the tour and read about how to ask good questions. Lastly please learn how to create a Minimal, Complete, and Verifiable Example. — Markus
– Markus, Commented Jun 19, 2017 at 7:38
@Markus Thank you for the comment. I just re-edit my question. Is it OK? — Baoquan Feng
– Baoquan Feng, Commented Jun 19, 2017 at 8:43
That's not just okay, it's really appreciated. ;) A last remark: You should make your question a bit more clear. Maybe adding details about what you have tried to resolve the error will help people knowing the answer to help you. — Markus
– Markus, Commented Jun 19, 2017 at 9:51

pfm · Accepted Answer · 2017-06-19 12:20:13Z

45

You also need to initialise the local variables hidden in the tf.metrics.recallmethod.

For example, this piece of code would work:

init_g = tf.global_variables_initializer()
init_l = tf.local_variables_initializer()
with tf.Session() as sess:
    sess.run(init_g)
    sess.run(init_l)

answered Jun 19, 2017 at 12:20

pfm

6,3484 gold badges42 silver badges44 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Random Certainty Over a year ago

@npf thanks for the answer, but could you please explain what the local_variables_initializer() does? It seems counterintuitive to me, since all the values needed to calculate recall are computed through the graph. What do the local_variables_initializer() do?

pfm Over a year ago

The local_variables_initializer will initialize the variables belonging to the LOCAL_VARIABLES collection. This is best described in the answers to this question stackoverflow.com/q/38910198/4282745

Collectives™ on Stack Overflow

TensorFlow: “Attempting to use uninitialized value” in variable initialization

1 Answer 1

2 Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related