moonhwan JeongTensorflow2.0 PGGAN: Progressive Growing of GANs for Improved Quality, Stability, and VariationHere, I introduce a simple code to implement PGGAN in Tensorflow 2.0.5 min read·Jan 13, 2021--1--1
moonhwan JeongUpdating old tensorflow codes to new tensorflow 2.0+ style.In this post I will introduce an example of how to update legacy tensorflow codes to new style. tensorflow 2.0 recommends using Keras…2 min read·Aug 8, 2020----
moonhwan Jeong3D Face Reconstruction: Make a Realistic Avatar from a PhotoIn this post, I’ll introduce techniques for reconstructing a 3D face from a Photo. Creating a unreal character from a picture is familiar…7 min read·Dec 20, 2019----
moonhwan JeongTensorflow-BEGAN: Boundary Equilibrium Generative Adversarial NetworksI’ve covered GAN and DCGAN in past posts. In 2017, Google published a great paper. The title of paper is “BEGAN: Boundary Equilibrium…5 min read·Apr 16, 2019--1--1
moonhwan JeongMake dataset from images in TensorflowA data-set is needed to train the model. In the last article, we covered the model for generating faces. I used Celeb_A dataset(link)…2 min read·Mar 14, 2019----
moonhwan JeongDCGAN-Tensorflow: For more stable trainingSince Ian Goodfellow’s paper, GAN has been applied to many fields, but its instability has always caused problems. The GAN has to solve…4 min read·Mar 8, 2019--1--1
moonhwan JeongGAN with Tensorflow: Basics of Generative Adversarial NetworksMachine learning is generally classified into three types: Supervised learning, Unsupervised learning and Reinforcement learning.5 min read·Feb 21, 2019----