dhingratul

Face-Recognition

In this thesis, we study two problems based on clustering algorithms. In the first problem, we study the role of visual attributes using an agglomerative clustering algorithm to whittle down the search area where the number of classes is high to improve the performance of clustering. We observe that as we add more attributes, the clustering performance increases overall. In the second problem, we study the role of clustering in aggregating templates in a 1:N open set protocol using multi-shot video as a probe. We observe that by increasing the number of clusters, the performance increases with respect to the baseline and reaches a peak, after which increasing the number of clusters causes the performance to degrade. Experiments are conducted using recently introduced unconstrained IARPA Janus IJB-A, CS2, and CS3 face recognition datasets.

Face-Recognition-Algorithms

Implemented and evaluated four basic face recognition algorithms: Eigenfaces, Fisherfaces, Support Vector Machine (SVM), and Sparse Representation-based Classification (SRC) on YaleB dataset

generative-ai-with-llm

Various PoC/MvP for different libraries and use-cases supporting Generative AI workflows.

Model-Compression

Reduce the model complexity by 612 times, and memory footprint by 19.5 times compared to base model, while achieving worst case accuracy threshold.

Player-Tracking

Tracks the wide receiver from a single shot video clip, where the offensive team is to left

scene-clustering

Clustering scenes

Sequence-Models

Course 5 from deeplearning.ai

Stock-Price-Prediction

Stock price prediction using LSTM and 1D Convoltional Layer implemented in keras with TF backend on daily closing price of S&P 500 data from Jan 2000 to Aug 2016

Unified-Face-Landmark-and-Gender-Recognition

Face Detection, landmark detection and gender classification in a unified workflow

electoral_rolls

PDFs of Indian Electoral Rolls

dhingratul/Eclectic-Nets

Collection of most popular Deep Learning architechtures trained with tensorflow, keras

dhingratul/openai-api-short

Short course on Generative AI from DeepLearning AI

dhingratul/RAG

RAG, and Adavanced RAG methods

dhingratul/generative-ai-with-llm

Various PoC/MvP for different libraries and use-cases supporting Generative AI workflows.

dhingratul/build-nanogpt

Video+code lecture on building nanoGPT from scratch

dhingratul/chess-com-pgn-downloader

chess.com PGN downloader

dhingratul/copilot-test

copilot-test

dhingratul/custom_github_actions

dhingratul/dataset_viewer

dhingratul/DeepRL-Agents

A set of Deep Reinforcement Learning Agents implemented in Tensorflow.

dhingratul/dhingratul.github.io

Personal Website

dhingratul/github-actions

Primer to Github Actions

dhingratul/gorilla

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

dhingratul/JEP

dhingratul/lightweight-human-pose-estimation.pytorch

Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.

dhingratul/LiveChess2FEN

Predict live chess games into FEN notation.

dhingratul/local-agent

learning resource of langgraph for dummy

dhingratul/machine-learning-engineering-for-production-public

Public repo for DeepLearning.AI MLEP Specialization

dhingratul/mcp-server

dhingratul/models

Models and examples built with TensorFlow

dhingratul/mojo

The Mojo Programming Language

dhingratul/multi_agent_bot

dhingratul/nanoGPT

dhingratul/nanoGPT-1

The simplest, fastest repository for training/finetuning medium-sized GPTs.

dhingratul/pdfhextractor

Extract Highlights from PDFs

dhingratul/RL-Specialization

Part of RL Specialization offered by U. Alberta

dhingratul/sapiens

High-resolution models for human tasks.

dhingratul/stanford-tensorflow-tutorials

This repository contains code examples for the Stanford's course: TensorFlow for Deep Learning Research.

dhingratul/tensorflow

Computation using data flow graphs for scalable machine learning

dhingratul/terraform-getting-started

terraform-getting-started