I built a Streamlit tool that turns my raw LinkedIn data export into charts, word clouds, and LLM-driven topic analysis of everything I’ve ever posted — all running locally via Ollama, with no data leaving my machine.
I built a Streamlit tool that turns my raw LinkedIn data export into charts, word clouds, and LLM-driven topic analysis of everything I’ve ever posted — all running locally via Ollama, with no data leaving my machine.
An open-source Unity 6 / OpenXR video player for the Samsung Galaxy XR headset. Plays 180° side-by-side 3D content with independent pitch repositioning, hand-tracking pinch UI, and optional eye-tracking gaze targeting.
A native Android XR app that plays 180° side-by-side stereoscopic video on a curved hemisphere in full-space mode. Built with Jetpack XR, SceneCore, and Media3/ExoPlayer.
I built a pipeline that automatically generates AI commentary and voiceover for gameplay videos — using GPT-4o Vision to analyze frames and TTS to narrate them. Built days after the GPT-4 Vision API launched in November 2023, it is one of the earliest known implementations of this approach.
I helped in the release of Caldera dataset from Activision
Adversarial Attack on Computer Vision Models Link to presentation Find in Github An adversarial attack on machine learning models refers to the deliberate manipulation of input data to cause a machine learning model to produce incorrect or unintended...
WhatsApp Meme Detector Find in Github I have been thinking of clearing some space in my phone for a long time. I have a lot of images in my whatspapp images folder- around 37,000 images. There are some pictures important to me in these 37k images which I donot want to...
• Implemented an aim assist python script that shoots at the body or the head of the enemy if the head is detected.
• Trained a YOLO 5 model with 92% accuracy and 20fps speed to detect head and body of the enemy in CSGO.
• Built a game agnostic bot so that it can be used in other FPS games with minimal training.
Heart arrhythmia detection uses machine learning based anomaly detection techniques inorder to detect irregularities in heartbeat pattern and future work is to notify the person using a realtime alert.
Hand Cricket Using OpenCV and Mediapipe Find in Github Hand Cricket using OpenCV & MediaPipe This project is an interactive computer vision application that recreates the classic Indian game of hand cricket using real-time hand gesture recognition. Built using...
The time between subsequent eye blinks and makes it available for data analysis
Sentiment Analysis on IMDB Movies Watch Video Github Sentiment classification is one of the basic problems in Machine Learning. Here, I have build a Flask based UI for a sentiment analysis model made using LSTM and hosted in...
Video Based on Similarity from tSNE Plot Youtube video Find in Github Download any 1000 or more ‘appropriate’ and publicly available images from the web. This could be part of a data set or something specific that you picked up or are interested in. Apply...
Model Based Machine Learning Drift Detection Find in Github The idea is to remove the Y labels from the training data set and label half of the training data as zero and the other half as one. A machine learning model is fit on the modified data set and the test data...
Spam Classification Using Logistic Regression Find in Github We will be looking at Spam Filtering with a real data set that has a “label” for every email – i.e. spam or not spam. We will use logistic regression classifier to solve this assignment and...
Detect elephants and birds and play sounds that scare them using a raspberry pi running PyTorch and alert farmers using telegram
In association with UC Berkeley
A Rasa chatbot that has a flirtatious persona, and has country search, language search, and location search capabilities
Easily find the cost of 3d prints