Uncategorized

Originally posted on : https://medium.com/mlearning-ai/anime-illustration-colorization-with-deep-learning-part-2-62b1068ef734 Introduction This is an update on my previous article Anime Illustration Colorization with Deep Learning — Part 1. If you have not read that, I recommend you to read it first and then come back. Anime Illustration Colorization with Deep Learning This project aims to create… medium.com After posting the previous …

Deep Learning Project — Anime Illustration Colorization — Part 2 Read More »

Originally posted on : https://medium.com/mlearning-ai/anime-illustration-colorization-with-deep-learning-9e7d7de7ee0b Introduction This project aims to create a deep learning model to learn a mapping from a non-colored anime illustration (sketch) to a colored version. We will use the Pix2Pix GAN to achieve this. 1. Dataset First of all, we need a dataset, a dataset that contains a set of non-colored …

Deep Learning Project — Anime Illustration Colorization — Part 1 Read More »

Originally posted on : https://medium.com/analytics-vidhya/the-ultimate-handbook-for-opencv-pillow-72b7eff77cd7 Introduction OpenCV and Pillow are the commonly used libraries in Python for image processing. In this article, I will list out all the codes that I think are useful regarding OpenCV and Pillow side by side, so that you can compare them easily. Updates 15-Jun-22: Added [13. RGBA to RGB]. 0. …

The Ultimate Handbook for OpenCV & Pillow Read More »

Originally posted on : https://medium.com/mlearning-ai/how-normalization-affects-image-styles-edec31841bb4 In Style Transfer and some generative networks, special normalization layers such as CIN, AdaIN are used to control the style of the output image. But how and why does a normalization layer affect image style? It is crucial to understand the rationale behind it in order to know why they …

How Does Normalization Layer Affect Image Styles? What is AdaIN? Read More »

Originally posted on : https://medium.com/better-programming/how-to-beat-wordle-every-day-an-easy-cheat-3c1dc51bc4fc 2 ways to quickly solve the viral puzzle Unlike my usual articles, this one is not about deep learning or computer vision. This is about a popular web game called Wordle. Since I have been seeing a lot of people sharing their daily Wordle results on social media recently, it makes …

How to Beat Wordle Every Day! An Easy Cheat Using Browser Console Read More »

Originally Posted on: https://medium.com/mlearning-ai/sefa-finding-semantic-vectors-in-latent-space-for-gans-9573c557f21e Paper Explained: SeFa — Closed-Form Factorization of Latent Semantics in GANs Motivation The generator in GANs usually takes a randomly sampled latent vector z as the input and generates a high-fidelity image. By changing the latent vector z, we can change the output image. However, in order to change a specific attribute in the output image (e.g. …

SeFa — Finding Semantic Vectors in Latent Space for GANs Read More »

Originally posted on: https://medium.com/@steinsfu/stylegan3-clearly-explained-793edbcc8048 Paper Explained: StyleGAN3 — Alias-Free Generative Adversarial Networks The StyleGAN3 paper is pretty hard to understand. In this article, I tried my best to reorganize it and explain it step by step. Hope you understand it better after reading this. If you want to know the difference and evolution of StyleGAN, …

StyleGAN3 Clearly Explained! Read More »

Originally posted on: https://medium.com/@steinsfu/stylegan-vs-stylegan2-vs-stylegan2-ada-vs-stylegan3-c5e201329c8a In this article, I will compare and show you the evolution of StyleGAN, StyleGAN2, StyleGAN2-ADA, and StyleGAN3. Note: some details will not be mentioned since I want to make it short and only talk about the architectural changes and their purposes. Table of Contents StyleGAN∘ Step 1: Mapping and Styles∘ Step 2: Constant Input∘ Step 3: Noise Inputs∘ Step …

StyleGAN vs StyleGAN2 vs StyleGAN2-ADA vs StyleGAN3 Read More »

Originally posted on: https://medium.com/codex/jojogan-style-transfer-on-faces-using-stylegan-create-jojo-faces-cc0907a9bc6 Paper Explained: JoJoGAN — One-Shot Face Stylization Introduction JoJoGAN is a style transfer procedure that let you transfer the style of a face image to another style. It accepts only one style reference image and quickly produces a style mapper that accepts an input and applies the style to the input. Although it is called JoJoGAN, it can …

JoJoGAN — Style Transfer on Faces Using StyleGAN — Create JoJo Faces (with codes) Read More »

Originally posted on : https://medium.com/@steinsfu/diagonalgan-content-style-disentanglement-in-stylegan-explained-609d1407f010 Paper Explained: Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation Introduction In image generation, Content-Style Disentanglement has been an important task. It aims to separate the content and style of the generated image from the latent space that is learned by a GAN. Content: spatial …

DiagonalGAN — Content-Style Disentanglement in StyleGAN Explained! Read More »