Unan Anan is a CEO and hands-on software engineer based in São Paulo with eight years of experience across Windows, Linux, macOS, iOS and Android environments. He blends leadership with practical machine learning engineering, notably improving PFLD-based face alignment training and integrating ncnn inference on HiSilicon 35xx platforms. Comfortable across desktop and mobile stacks, he fixes hard edge cases like occlusion and wing loss in production models. Known on GitHub for pragmatic, efficiency-minded contributions (self-described as a "lazy layman"), he favors robust, maintainable solutions over flashy experiments.
Contributions summary:Unan primarily focused on improving and releasing an existing PFLD (PFPLD) training code, which is related to face alignment. They contributed by integrating ncnn models and inference code. Further contributions include fixing bugs in relation to the hdface module and test.py. The user added a robust model and addressed issues related to wing loss and occlusion.
Contributions:10 commits, 37 pushes, 1 branch in 1 year 2 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.