SHUBHAM GARG's Projects
A real-time chat application built with Node.js, Express, and Socket.io, featuring end-to-end encryption (E2EE) using RSA-OAEP. Users can join chat rooms, send encrypted messages, and use an emoji picker. Ensures privacy with sender-side encryption and recipient-side decryption. Future enhancements include user authentication and file sharing.
This repository contains an implementation of a Deep Convolutional Generative Adversarial Network (DCGAN) trained on the FashionMNIST dataset. The project aims to generate realistic images of clothing items using a GAN architecture. It includes model definitions, training scripts, and visualizations of generated images at various training stages.
This project aims to investigate temperature changes over time and predict future temperature patterns on a regional and global scale. We employ time series forecasting methods, including neural networks, ARIMA, and SARIMAX, using the GISTEMP v4 dataset from NA
A project for lung disease detection and analysis using deep learning. It includes lung segmentation, disease classification, and severity localization with Grad-CAM for visual explanations. This repository provides code, datasets, and documentation for replication and further research.
A personal portfolio website built with Django and hosted on Heroku. This responsive portfolio showcases my skills, projects, and experiences, featuring a project showcase, skills section, contact form, and about me section. Tech stack includes Django, HTML, CSS, JavaScript, and Bootstrap.
OneFormer: One Transformer to Rule Universal Image Segmentation, arxiv 2022 / CVPR 2023
Add your Python Scripts!:)
WhatsApp Clone
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
A latent text-to-image diffusion model
This repository implements a Vision Transformer (ViT) to classify handwritten digits from the MNIST dataset. The project includes model definition, training scripts, and visualization of results, including correct/incorrect predictions and a confusion matrix.
A simple bot to automate 1000's of messages on whatsapp
This repository contains an implementation of a deep learning approach for yoga pose classification using Convolutional Neural Networks (CNN) and MediaPipe for body keypoint detection. The project aims to classify various yoga poses with high accuracy and low latency, making it suitable for real-world applications.