Alexander Nohe’s Post

🔮 Excited to share my latest project! I've developed a GUI-based Gemstone Price Prediction App using Streamlit and machine learning techniques. 📊 This app provides insights into gemstone pricing trends by analyzing various factors such as carat, cut, color, clarity, depth, table, and dimensions. 🧠 Leveraging XGBoost regression model, the app predicts gemstone prices with remarkable accuracy. 📈 Users can explore interactive visualizations including scatter plots, box plots, line plots, histograms, and bar charts to understand the relationships between different gemstone attributes and prices. link for a gemstone application:- https://lnkd.in/gMarS3Kq #MachineLearning #DataScience #Gemstones #Streamlit #DataVisualization #PredictiveAnalytics

I'm thrilled to share my recent project on OpenCV named #HandTune, an hand gesture volume control app built with OpenCV and Google Media Pipeline! 📱✋ With HandTune, you can adjust your device's volume with simple hand gestures, making interaction more intuitive and seamless. It's a great example of how AI can enhance our daily lives in unexpected ways. Feel free to check it out on github: https://lnkd.in/dkv8sR9n Demo Video👇: #TechInnovation #HandGestureControl #OpenCV #GoogleMediaPipeline #AppDevelopment

Building AI-powered apps with Streamlit and Trulens In this video as part of the Streamlit Cookbook series, Chanin Nantasenamat, Senior Developer Advocate for Streamlit at Snowflake chats with Josh Reini, Developer Advocate for Trulens at Snowflake, on how to use Trulens with Streamlit to build AI apps. TruLens is a software tool that helps you to objectively measure the quality and effectiveness of your LLM-based applications using feedback functions. Feedback functions help to programmatically evaluate the quality of inputs, outputs, and intermediate results, so that you can expedite and scale up experiment evaluation. Use it for a wide variety of use cases including question answering, summarization, retrieval-augmented generation, and agent-based applications.   📺 Watch Tutorial Video: https://lnkd.in/gfJwxqNb 🕹️ Demo app: https://lnkd.in/gwcgcYz5 🐙 GitHub repo https://lnkd.in/gdzR3XqS #streamlit #trulens #cookbook

OpenAI Real Time API live in inside of an application. I've got to say, after playing around with this, I am extremely excited to see where AI inside of applications is going. Imagine building a meal plan app that allows you to speak directly with the advanced voice mode in order to recommend certain meals, in real time! Here is the full video: https://lnkd.in/gzkAR_A8

Build a Landmark Classifier to Enhance Photo Sharing Apps In this project, I use my CNN skills to build a landmark classification model. This project tackles a real-world challenge faced by photo sharing apps: automatically inferring location data from images. The model i build will: * Analyze photos for landmarks * Classify landmarks to predict location This project offers a comprehensive ML experience, taking through all stages of the design process: * Data Preprocessing * CNN Design and Training * Model Comparison * App Deployment #AWS #Udacity #machinelearning #cnn #landmarkclassification #photosharing

🚀 Excited to share my latest project - an interactive Streamlit app for visualizing Decision Surfaces on different Datasets.!🤖 💻 Under the guidance of my trainer SAXON K SHA sir at Innomatics Research Labs, I had the opportunity to develop this app as part of Deep Learning course. It's been an incredible learning journey, and I'm thrilled to showcase the results. 🔍 With this app, you can explore various datasets such as ushape, concentriccir1, concentriccir2, linearsep, outlier, overlap, xor, twospirals , random and see how different datasets classify data points, helping to understand their decision boundaries. 🔗 Streamlit Deployment : https://lnkd.in/gmXeYhS7 📊 Features: Interactive selection of Datasets Interactive selection of Active Functions Interactive selection of Number of Epochs Interactive selection of Number of Hidden Layers Interactive selection of Number of Neurons in Hidden Layers #MachineLearning #DataScience #Streamlit #DecisionSurfaces #InnomaticsResearchLabs #InteractiveApp

Building AI-powered apps with Streamlit and TruLens. Chanin Nantasenamat, PhD, Senior Developer Advocate for Streamlit at Snowflake chats with Josh Reini, Developer Advocate for TruLens at Snowflake, on how to use TruLens with Streamlit to build AI apps. TruLens is a software tool that helps you to objectively measure the quality and effectiveness of your LLM-based applications using feedback functions. Use it for a wide variety of use cases including question answering, summarization, retrieval-augmented generation, and agent-based applications.   📺 Watch the tutorial: https://lnkd.in/gfJwxqNb 🕹️ Demo app: https://lnkd.in/gwcgcYz5 🐙 GitHub repo: https://lnkd.in/gdzR3XqS

Excited to Share My Latest Project! I have developed a Streamlit app that finds similar images using OpenCV, scikit-image for advance image analysis, and color histogram for feature vector calculation. With this app, you can easily upload an image and find the most similar images from a pre-defined database. This can be particularly useful for applications in computer vision, such as content-based image retrieval, duplicate image detection, and more. Check out the app and let me know what you think! Your feedback and suggestions are always welcome. 😊 https://lnkd.in/dumn3JbG #ComputerVision #ImageProcessing #MachineLearning #DataScience

Excited to share a project I've been working on: a Real Estate Sales Price Predictor, now live on Hugging Face Spaces! This application uses a trained Random Forest model to predict property sales prices based on key features like Assessed Value, Sales Ratio, and more. I built it from scratch, performing extensive exploratory data analysis, feature selection, and model evaluation to ensure robust performance. Now, it's available as an interactive web app, allowing users to input property details and receive a sales price estimate instantly. Check it out here: https://lnkd.in/gdJrkVDs I'm particularly proud of the model's accuracy and the process of bringing it all together — from data cleaning, feature engineering, to model training, and finally deploying it as a user-friendly app on Hugging Face. A big shoutout to the tools and libraries that made this possible: Pandas, Scikit-Learn, SHAP for interpretability, and of course, Hugging Face for deployment. If you're curious about the process or have any feedback, I'd love to hear your thoughts! #MachineLearning #DataScience #RealEstate #HuggingFace #RandomForest #AI

The code is a Streamlit web application for image processing. It allows users to upload an image and apply various filters and transformations to the image. The app also provides histograms to show the pixel value distribution before and after processing. Kaggle -->[https://lnkd.in/dh9ZbD9e]