This project focuses on environmental monitoring of two major rivers in Kathmandu, Nepal — Bagmati and Bishnumati. Using drone-captured aerial imagery, we have constructed a dataset aimed at detecting and segmenting river waste.

Research component focused on identifying dengue breeding points using UAV imagery and YOLOv8 deep learning models.

A deep learning project implementing YOLOv8 for multi-class waste detection and classification using the TACO dataset.

Lightweight Kubernetes FinOps CLI — analyze resource usage, detect waste, and get rightsizing recommendations without installing anything in your cluster.

AI tool that identifies waste from images and recommends proper disposal to help the environment.

YOLOv8 object detection and U-Net segmentation for waste classification on TACO dataset

Deep Learning project for waste object detection and segmentation using YOLOv8 and U-Net on the TACO dataset. Implements object detection with YOLOv8 for bounding boxes and custom U-Net for pixel-wise segmentation. Includes EDA, data augmentation pipeline, and comparative analysis. Built with PyTorch for CS4045 course project.

The Maltese Domestic Dataset (MDD) is an open-source collection of annotated images of domestic waste bags captured in Maltese urban environments. It supports computer vision research by providing labelled data for training and evaluating object detection models that identify and categorise different types of waste bags.

🌱 A smart waste detection app that classifies trash types (plastic, metal, glass, paper) using a machine learning model. Built with React, Express, and Flask. The frontend 👇

Waste detection system using YOLOv5 for real-time object detection and classification of waste types.

YOLOv10 for waste classification - baseline and fine-tuned training on TACO dataset

Build and run native iOS and Android clients for Codex with support for accessibility, network discovery, and seamless SSH authentication.

Python code for Neuromatch Academy's Summer 2022 Deep Learning course project: Waste detection using Mask R-CNN on TACO dataset.

Scan CSS entropy and enforce quality gates in GitHub Actions

A personal project which aimed to build a disposable face mask type waste detector 😷 found in the environment (streets, forests, beach etc)

This is an AI-powered waste classification application that uses computer vision to detect and categorize different types of waste materials.

This is an AI-powered waste classification application that uses computer vision to detect and categorize different types of waste materials.

Multi-cloud FinOps & Security CLI for AWS, GCP, and Azure. Identify cost waste, detect security vulnerabilities, and discover optimization opportunities across your cloud infrastructure.

International Contest on Illegal Waste Dumping Detection

This project focuses on environmental monitoring of two major rivers in Kathmandu, Nepal — Bagmati and Bishnumati. Using drone-captured aerial imagery, we have constructed a dataset aimed at detecting and segmenting river waste