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

Zero to Hero: A Quick Guide to Object Tracking: MDNET, GOTURN, ROLO

by Ankit Sachan • April 29, 2021

  In today’s article, we shall deep dive into video object tracking. Starting from the basics, we shall understand the need for object tracking, and then go through the challenges and algorithmic models to understand visual object tracking, finally, we shall cover the most popular deep learning based approaches to object tracking including MDNET, GOTURN, […]

Continue Reading

Using gpus Efficiently for ML

by Ankit Sachan • November 24, 2020

In this blog post, we will look into how to use multiple gpus with Pytorch. We will see how to do inference on multiple gpus using DataParallel and DistributedDataParallel models of pytorch. Same methods can also be used for multi-gpu training. Pytorch provides a very convenient to use and easy to understand api for deploying/training models […]

Continue Reading