Marika Wei

I used these params to finetune and they worked great, actually overfitted and I had to go back and pick earlier epochs. ``` --keep_probability 0.6 \ --weight_decay 5e-4 \ --people_per_batch...

@kifaw The triplet loss script of course. I went through a bunch of old issues on triplet loss and ended up with that

@Var-ji I merged folders from VGGFace2 and the deepglint asian celebrity dataset. Tried training from scratch but it didn't work, I ended up taking the softmax model and finetune it...

@Var-ji That validation rate can’t be right. I trained many times and val rate is always slightly below accuracy once it goes above 0.9, so if acc is 0.99 then...

Here's tensorboard lfw graphs using arcface loss, don't have logs anymore for others, triplet loss looks similar enough. I use training scripts from this repo, the code is good enough...

Not sure what you are trying to accomplish but you could simply pass ssl options on. I wrote a [short article](https://mw.gl/posts/elixir_ssl/) on `verify_fun` that shows how to do certificate pinning,...

I can confirm timeout is not working as expected in 1.4.9