Count the MACs / FLOPs of your PyTorch model.

Functional models and algorithms for sparse signal processing

This codebase demonstrates how to synthesize realistic 3D character animations given an arbitrary speech signal and a static character mesh.

Acceptance rates for the major AI conferences

This project is part of a research paper that was presented as a poster at ICPRAM 2020. It highlights the use of discriminative neural networks to tackle the problem of class imbalance.

COVID19 India Tracker, predictive analytics and research. Built by engineers, data scientists, AI and medical professionals.

corona india main webpage repo

Streaming torrent client for node & the browser

NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

My submissions for interviewstreet.com CodeSprints.