Series

Machine Learning

Developing a good ML/AI based product is a hell lot more than just a state-of-the-art model. This is my attempt to help you out & look beyond the models because it's just an idea that all you need 💡

Articles in this series

Understanding current AI industry expectation

May 23, 20214 min read 66 views

1. The Past Expectation It is vital to understand the past responsibility to adapt to the current expectation of the industry. The AI space was still relatively new (though not in academics) and many companies, startups were analyzing its applicati...

Understanding current AI industry expectation

A complete guide to building a Docker Image serving a Machine learning system in Production

Feb 12, 202110 min read 77 views

A complete step-by-step guide for building a Docker image (GPU or CPU) along with explaining all best practices that should be followed which will be

A complete guide to building a Docker Image serving a Machine learning system in Production

Working with Hugging Face Transformers and TF 2.0

Apr 24, 20208 min read 49 views

Models based on Transformers are the current sensation of the world of NLP. Hugging Face’s Transformers library provides all SOTA models (like BERT, GPT2, RoBERTa, etc) to be used with TF 2.0 and this blog aims to show its interface and APIs 0. Disc...

Working with Hugging Face Transformers and TF 2.0

Build a Custom ResNetV2 with the desired depth

Apr 5, 20207 min read 45 views

This tutorial will help you to build a ResNet model with any desired no of depth/layer from scratch ResNet has been always one of my favourite architecture and I have used its core idea of skip connection many times. It is now fairly old as both Res...

Build a Custom ResNetV2 with the desired depth

MLOps: The Upcoming Shining Star

Jan 11, 20207 min read 42 views

The right path to building a full-stack machine learning system. MLOps is the new emerging practice to streamline managing the ML lifecycle.

MLOps: The Upcoming Shining Star