The Python Oracle

Is it thread-safe when using tf.Session in inference service?

This video explains
Is it thread-safe when using tf.Session in inference service?

--

Become part of the top 3% of the developers by applying to Toptal
https://topt.al/25cXVn

--

Music by Eric Matyas
https://www.soundimage.org
Track title: Quirky Dreamscape Looping

--

Chapters
00:00 Question
00:34 Accepted answer (Score 18)
01:18 Thank you

--

Full question
https://stackoverflow.com/questions/3869...

Accepted answer links:
[Session.run()]: https://www.tensorflow.org/versions/r0.1...
[sess.graph.finalize()]: https://www.tensorflow.org/versions/r0.1...

--

Content licensed under CC BY-SA
https://meta.stackexchange.com/help/lice...

--

Tags
#python #multithreading #tensorflow #tensorflowserving

#avk47



ACCEPTED ANSWER

Score 18


The tf.Session object is thread-safe for Session.run() calls from multiple threads.

Before TensorFlow 0.10 graph modification was not thread-safe. This was fixed in the 0.10 release, so you can add nodes to the graph concurrently with Session.run() calls, although this is not advised for performance reasons; instead, it is recommended to call sess.graph.finalize() before using the session from multiple threads, to prevent accidental memory leaks.