Yijun Yang

When I used AdaBound to train a ShuffleNet V2 model with tiny batch (5-10), I met same problem. This optimizer might not be convergent. Btw: when I used "adabound.AdaBound([{'params': part...

Hi, LeanderK. Thanks for your comment. You may misunderstand my purpose. There's no free lunch in this world indeed, so there's also no free lunch between exploration & exploitation for...

> Dear author, tnanks for sharing so wonderful work. I want to do a head pose task in wild world. The hopenet runs too slow and I found your work....

> @OverEuro, thanks for your great work. It is really helpful for me. > in training code of original project, the default alpha is 0.001, defalut epoch is 5, and...

> why Regression loss coefficient. is 0.001, deep-head-pose set alpha is 1 or 2 shuff_epoch_120.pkl was trained with alpha=1.

> @OverEuro > Thank you for your great work. > I am a freshman and when I use your lastest hopenet-lite model with model shuff_epoch_120.pkl, just follow the sample as...

> Hi, > I ran original hopenet model and hopenet-lite model one after another. Though results were different(as supposed) but couldn't find any significant speed up in lite model. Did...

> Hello @OverEuro, > Thank you for this implementation. I have a few doubts that I wanted to clarify. > > 1. Does this model support head pose estimation under...

> @OverEuro, Thanks. > > So if I were to use an image with a resolution other than 224 x 224, is it absolutely necessary for me to resize it...

> Thank you for public your model and code. > Do you test your model in AFLW2000? How about the test result? I follow the test code in https://github.com/natanielruiz/deep-head-pose, and...