Understanding and improving Image to Image Translation Pix2PixHD

by Ankit Sachan • September 24, 2021

Introduction Photo-realistic image rendering using standard graphics techniques requires realistic simulation of geometry and light. The algorithms which we use currently for the task are effective but expensive. If we were able to render photo-realistic images using a model learned from data, we could turn the process of graphics rendering into a model learning and […]

Continue Reading
generating images using GAN

Understanding StyleGAN for Image Generation using Deep Learning

by Ankit Sachan • August 3, 2021

Introduction Images produced by generative methods have been improving lately. Most of the recent generative algorithms have made use of generative networks that are trained using a discriminator network as their adversary. Generative Adversarial Networks (GANs) or generators, in other words, are a relatively new concept in the field of computer vision. Their aim is […]

Continue Reading

State-Of-The-Art Text to Image Generation using DALL-E

by Ankit Sachan • July 13, 2021

DALL-E – Creating images from text Code – openai/DALL-E: PyTorch package for the discrete VAE used for DALL·E. Paper – https://arxiv.org/pdf/2102.12092.pdf   What is DALL-E? On 5th January 21, OpenAI unveiled their novel text to image generation model, DALL-E. This model is capable of generating various types of images from textual descriptions. A humongous 12 […]

Continue Reading
Accuracy on ImageNet

Training Image Classification 8x Faster With NFNet

by Ankit Sachan • June 18, 2021

Introduction: Anyone who has deployed a neural network on production knows that deploying a network is easy but making sure that it stays updated as new user data flows is a harder task. It involves keep training the network with new incoming data frequently and in such a case being able to train faster is […]

Continue Reading

Training Object Detectors using TensorFlow Object Detection API

by Ankit Sachan • May 31, 2021

Machine learning algorithms are everywhere around you. The recommendations you receive on youtube, estimation of commute time, face detection in google photos, and many more, all of these features that make our lives easier would not have been possible without advances in machine learning algorithms. Machine learning can be further classified into various fields; many […]

Continue Reading