Boris Polonsky

https://github.com/BorisPolonsky/zh-NER-TF/blob/1400c15cc47c878dd795326af43078d6dceb4df1/model.py#L56

I'm using official `tensorflow/serving:2.4.0-gpu` and I can't capture profiling data either. Tensorboard created events.out.tfevents.1608174858.faf5bf56d686.profile-empty in the logdir, prompted that Capture profile successfully, please refresh and shows "No profile data was...

> Hi, sorry for the late reply. I think the missing step is to bind a host volume location where tensorboard expects the profile data to be written to. >...

> > Do I have to mount -v /tmp/tfs:/tmp/tfs for both containers besides connecting them to the same docker network? > > No I don't think that is necessary. >...

> > No it isn't. (Since I didn't mount /tmp/tenosorboard for both both containers.) > > > > > The design does not work the way you have described. The...

> I think this is related to: [tensorflow/tensorflow#2626](https://github.com/tensorflow/tensorflow/issues/2626) Thanks for the reply. I've gone through the post and it doesn't seem to be the problem on tensorflow's side, yet it...

My configuration of `$LD_LIBRARY_PATH` via `-e` in my case looks exactly the same as this [pull request](https://github.com/tensorflow/serving/pull/1543), yet this workaround doesn't work in my case.

> @BorisPolonsky, > The issue here is that, since you want to use `Tensorflow Serving GPU`, the `Docker Run` Command should have the argument, `runtime` . > > Sample command...

> TIP: If you're running a GPU image, be sure to run using the NVIDIA runtime --runtime=nvidia. It was definetily declared as deprecated in the exactly wiki page you mentioned...

> @BorisPolonsky, > Can you please let us know what is the source of the information, > > > nvidia-docker 2 is deprecated, use Native GPU Support > > because...