ksmooi's repositories
deepstream_apps_cpp
Samples for TensorRT/Deepstream for Tesla & Jetson
triton_client
Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.
mscs_net_npp_linux_virtual
Network Principles in Practice: Linux Networking. You are welcome to run this code and I try to make it as self explanatory as possible, but some of the explanation will be in the videos for the course.
mscs_net_npp_linux_router
Network Principles in Practice: Linux. You are welcome to run this code and I try to make it as self explanatory as possible, but some of the explanation will be in the videos for the course.
mscs_net_npp_linux_intro
This set of demos and lab goes along with the coursera course: Network Principles in Practice: Linux. You are welcome to run this code and I try to make it as self explanatory as possible, but some of the explanation will be in the videos for the course.
mscs_dl_cnn_covid19_xray
This project aims to classify COVID-19 from X-ray images using Convolutional Neural Networks (CNN), leveraging a dataset of normal and pneumonia-affected lungs to assist in early diagnosis through radiological imaging.
mscs_ml_unsupervised_learning
Unsupervised learning finds patterns or structures in unlabeled data, useful for tasks like clustering and dimensionality reduction. It helps with preprocessing, discovering hidden patterns, and making data easier to visualize and analyze.
mscs_dl_cnn_cancer_detection
This project aims to develop a convolutional neural network (CNN) model to identify metastatic cancer in histopathologic images, leveraging a modified version of the PatchCamelyon (PCam) benchmark dataset for binary image classification.
mscs_dl_gan_monet_painting
This project uses Generative Adversarial Networks (GANs) to transfer the artistic style of Monet paintings to ordinary photos, creating realistic Monet-style images. The model is trained using a dataset of Monet paintings and photos, and evaluated for quality using metrics like FID.
mscs_dl_nlp_disaster_tweets
This project aims to classify tweets as disaster-related or not using GloVe embeddings and a GRU-based neural network, improving accuracy through various model configurations and regularization techniques.
mscs_ml_bank_marketing
This project aims to predict whether a client will subscribe to a term deposit using machine learning techniques applied to a bank marketing dataset. It involves data preprocessing, feature selection, dimensionality reduction, and evaluating various supervised learning models.
mscs_ml_student_performance
This project predicts students' final grades (G3) using machine learning based on their demographics and background.
mscs_big_data_email_verifier
The Email Verifier project is designed to efficiently handle email verification processes, utilizing RabbitMQ for messaging, Ktor for web server functionality, and consistent hash exchange for load distribution, ensuring scalability and reliability.
mscs_big_data_cap_theorem
This project enhances a real-time product inventory management system by integrating robust transaction management and an event-driven architecture to balance consistency, availability, and partition tolerance, ensuring accurate and reliable inventory tracking.
mscs_big_data_match_predictor
The Match Predictor project uses various machine learning models to predict soccer match outcomes, leveraging historical data and advanced algorithms to forecast results. The system includes a backend in Python with Flask and a frontend in TypeScript with React.
mscs_big_data_web_app
This project is a simple web application built with Flask, allowing users to submit their name and message, which are then displayed along with browser details. It is designed for easy deployment on Heroku.
mscs_big_data_system_design
StockVision is a comprehensive system designed for real-time stock market analysis and data management. It efficiently collects, stores, and analyzes stock data from the Yahoo Finance API, providing users with detailed insights and trends through a user-friendly web interface and RESTful API.
mscs_big_data_design_graphql
BeautyInsights 360 analyzes customer behavior, product performance, and sales trends for a beauty brand using Dgraph. It integrates data sources and employs analytics to deliver personalized recommendations and optimize strategies. The project ensures modularity and ease of use.