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 32 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 37 views

Building a Docker image is generally considered trivial compared to developing other components of a ML system like data pipeline, model training, serving infra, etc. But an inefficient, bulky docker image can greatly reduce performance and can even ...

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 19 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 27 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 22 views

Why in the world shouldn’t I prioritize building ‘The Perfect Model’? Before reading further, I would suggest you read this paper. It discusses all of the related problems in detail. The major hurdles that generally arise while developing ML apps a...

MLOps: The Upcoming Shining Star