TensorBoard profile showing high usage of relu about serving HOT 6 CLOSED

@law-lin, I am not sure why FusedMatMul shows as Relu ops in Tensorboard graph. I think relu op will represent that particular layer of the graph and include all process in that layer like matmul, relu etc but I am uncertain.
Can you raise this issue in tensorboard repository for better assistance. Thanks.

from serving.

@singhniraj08 Makes sense. We're also seeing a high usage of SparseToDense in another model. Do you know if increasing the TF thread pool count in the CPU can help optimize SparseToDense?

from serving.

@law-lin,

I could find much on SpareToDense op to assist you, but got Working with sparse tensors for efficient use of sparse tensors in Tensorflow graph if that helps. Thank you!

from serving.

This issue has been marked stale because it has no recent activity since 7 days. It will be closed if no further activity occurs. Thank you.

from serving.

This issue was closed due to lack of activity after being marked stale for past 7 days.

from serving.

Are you satisfied with the resolution of your issue?
Yes
No

from serving.