This course covers the learning outcomes and goals of understanding image to image translation using Pix2Pix GAN. The course teaches the implementation of a PatchGAN discriminator for classifying N×N patches in an image as real or fake. The teaching method includes a review of the original paper, walkthrough of key concepts, and explanations of generator and discriminator architectures. The intended audience for this course includes individuals interested in image processing, GANs, and deep learning techniques.
Overview
Syllabus
Image to image translation (Pix2Pix) A review of the original paper and Understanding the key concepts
Walkthrough - Key details from the original paper
Generator architecture (U-Net)
Discriminator architecture (PatchGAN)
Next Tutorial: Satellite images to maps
Following Tutorial: Generating realistic- looking scientific images
Taught by
DigitalSreeni
Related Courses
-
Apply Generative Adversarial Networks (GANs)
-
Building Generative Adversarial Networks
1.0 -
Build Basic Generative Adversarial Networks (GANs)
-
Unpaired Image to Image Translation Using CycleGAN - An Introduction
-
Single Image Super Resolution Using SRGAN
-
TransGAN - Two Transformers Can Make One Strong GAN - Machine Learning Research Paper Explained
