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
Tensorflow tutorials

A quick complete tutorial to save and restore Tensorflow 2.0 models

by Ankit Sachan • July 17, 2020

Update: This article has been updated to show how to save and restore models in Tensorflow 2.0. If you want to learn the same with Tensorflow1.x, please go to this earlier¬†article that explains how to save and restore Tensorflow 1.x models. In this Tensorflow 2.X tutorial, I shall explain: What is a Tensorflow-Keras Model API? […]

Continue Reading