Arijit Das's Projects
CPU and GPU-accelerated Machine Learning Library
Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.
A Solution Accelerator for the RAG pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences. This includes most common requirements and best practices.
Cheetah: A Functional Programming Approach to Machine Learning
Optical Character Recognition using Deep Learning
End to End fine tuning for RAG models using PyTorch Lightning, Hydra, W&B and MosaicML Streaming
A high-performance AI trading platform and event-driven backtester
A Foundation for Scalable Cross-Platform Apps
Creating ChatGPT like experience on enterprise data using the Retrieval Augmented Generation pattern to
A dashboard for training, testing and evaluating Fair Machine Learning Algorithms
Vision AI Solution Accelerator
"The purpose of abstraction is not to be vague, but to create a new semantic level in which one can be absolutely precise" - Edsger Dijkstra
Code for ICE-BeeM paper
Multiple object tracking using Kalman Filter and Hungarian Algorithm - OpenCV
Fast k nearest neighbor search using GPU
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.
A pytorch-based deep learning framework for multi-modal 2D/3D medical image segmentation
PyTorch Lightning training library for Hugging Face Transformer models on AWS Sagemaker
AI Toolkit for Healthcare Imaging
NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day