Ganesh Anand

@andreasjansson Can I take this up? I'm trying to get familiar with the go part of the codebase and learn go. It seems like a simple enough place to start.

@bfirsh Okay. Just checking if anyone else was working on it. I'll take a look at #408 first.

@bfirsh If status is added as an attribute to Experiment and then updated when getting experiment details from the daemon it doesn't seem necessary. It seems there was a PR...

Is this a help wanted issue? I can submit a PR if so.

I have it almost ready. I'll test it against the tensorflow/models implementation and submit the PR in a few days.

Hopefully I'll finish it in 3-4 days. Just been busy. You can try PRing though if in a hurry. :)

@G-Bong I have a fork with TRT engine conversion added. https://github.com/gan3sh500/retinaface-pytorch

@G-Bong go ahead. It is mostly modified from the links I mention in the code. That code is just specific for single input, single output.

@SthPhoenix Ah yes. Outputs are flatten. Should reshape back.