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

by

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.

More Related Contents:

  1. How to prefetch data using a custom python function in tensorflow
  2. How to get the return value from a thread in Python?
  3. How to save/restore a model after training?
  4. Updating GUI elements in MultiThreaded PyQT
  5. How to limit execution time of a function call?
  6. Python threading multiple bash subprocesses?
  7. Python threads all executing on a single core
  8. How to close a thread when multithreading? [duplicate]
  9. Unable to load files using pickle and multiple modules
  10. Thread Safety in Python’s dictionary
  11. Failed to get convolution algorithm. This is probably because cuDNN failed to initialize,
  12. Can Keras with Tensorflow backend be forced to use CPU or GPU at will?
  13. Start a flask application in separate thread
  14. ImportError: No module named tensorflow
  15. Thread vs. Threading
  16. Python 3 Multiprocessing queue deadlock when calling join before the queue is empty
  17. Python code performance decreases with threading
  18. Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_2/convolution’
  19. Dimension of shape in conv1D
  20. Replacing placeholder for tensorflow v2
  21. In PyQt, what is the best way to share data between the main window and a thread
  22. Trying to fix tkinter GUI freeze-ups (using threads)
  23. error: can’t start new thread
  24. Deadlock with logging multiprocess/multithread python script
  25. Execute multiple threads concurrently
  26. How to install Tensorflow on Python 2.7 on Windows?
  27. How to handle non-determinism when training on a GPU?
  28. ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [8, 28, 28]
  29. waiting for user input in separate thread
  30. How is the Keras Conv1D input specified? I seem to be lacking a dimension

Leave a Comment