Ajit Kumar's Projects
π A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
Looking into more advanced topics of Python such as Multiprocessing, Asyncio, Custom logging, Closures etc.
A look into some of the advanced topics of SQL based on PostgreSQL
The all-in-one Desktop & Docker AI application with full RAG and AI Agent capabilities.
Design a model to predict the likelihood of installation based on the available parameter
A curated list of awesome Machine Learning frameworks, libraries and software.
An opinionated list of awesome Python frameworks, libraries, software and resources.
A project where we see the crucial role of feature selection and ordinal features in the data
The uncompromising Python code formatter
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
Changing the Green background of an image using the K means method.
π₯π₯π₯AI-driven data management platform Over 1 million developers are using Chat2DB
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
Making large AI models cheaper, faster and more accessible
A cross-platform command-line utility that creates projects from cookiecutters (project templates), e.g. Python package projects, C projects.
PyTorch package for the discrete VAE used for DALLΒ·E.
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
Binary classification on numerical dataset using different Sklearn models and Neural network
Hotel bookings for the Berlin Hospitality Market
Code examples and resources for DBRX, a large language model developed by Databricks
The implementation of DeBERTa
Text recognition (optical character recognition) with deep learning methods, ICCV 2019
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
A learning experience with models like GANs
PyTorch code and models for the DINOv2 self-supervised learning method.