Warning message "Tune using inter_op_parallelism_threads for best performance"

I noticed (when running DL Network Executor node with Keras model) the warning message: “Tune using inter_op_parallelism_threads for best performance.”

Is there any guide on how to do this? I think it has something to do with using the DL Python Network Executor node + Python code. Am I on the write track?

Thanks for any help!

EDIT: I was using tensorflow-mkl 1.12 when I wrote this. I switched to tensorflow-mkl 1.13.1 and the message went away.

1 Like

Thanks for sharing your solution! :slight_smile:

1 Like