Varadh Kaushik's starred repositories
DALLE2-pytorch
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
stable-diffusion-webui
Stable Diffusion web UI
trade-recommendations
This repository contains the implementation of a transformer-based model combined with a Proximal Policy Optimization (PPO) model to generate trade recommendations. The project leverages the predictive capabilities of transformers for price forecasting and the strategic decision-making of reinforcement learning.
PredictMD-SymptomDiseasePredictor
A comprehensive diagnostic pipeline that uses symptom data to predict diseases using state-of-the-art machine learning models like SVM and XGBoost.
Ecom-Review-Sentiment
Leveraging the Naive Bayes Classification algorithm and web scraping with BeautifulSoup, this project analyzes sentiments in e-commerce product reviews.
BankLoan-NN-Predictor
This project utilizes feed-forward neural networks with regularization and the Adam optimizer to predict outcomes from the Loan dataset, achieving up to 80.23% accuracy with insightful performance visualizations such as ROC curves and confusion matrices.
CNN-CIFAR10-ImageLab
This project uses TensorFlow and Keras to develop and optimize CNN models for classifying CIFAR-10's 60,000 32x32 color images across 10 classes, with evaluations via accuracy metrics and hyperparameter tuning.
AutoImageCaption-CNNvsResNet
"AutoImageCaption-CNNvsResNet" leverages the Flickr 8k Dataset to automate image captioning, comparing CNN+LSTM and ResNet+GRU models using BLEU scores for performance evaluation.
GovFoodSafety-Insight-Engine
The Food-Facility-Compliance-Engine leverages advanced ETL and BI technologies to process and visualize inspection data from Sonoma County's official government database, boosting compliance and safety in local food facilities.
IMDB-Data-Deep-Dive
FilmFlux Analytics : An advanced ETL-to-BI pipeline, transforming movie data into dynamic insights with Alteryx, MySQL, and Talend, visualized through Power BI and Tableau dashboards.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
Hazard-View-Bird
Efficient model for semantic segmentation on edge devices, specifically targeting the analysis of disaster scenes from images captured by unmanned aerial vehicles (UAVs).
Hazard-View-Bird
Efficient model for semantic segmentation on edge devices, specifically targeting the analysis of disaster scenes from images captured by unmanned aerial vehicles (UAVs).
AI-Character-Forge
Advanced AI-driven tool for generating unique video game characters using Stable Diffusion, DreamBooth, and LoRa adaptations. Enhances creativity with customizable, high-quality character designs, tailored specifically for game developers and artists.
CassavaHealth-AI
Based on my published research paper, this project uses a "One-vs-All" deep learning approach with EfficientNet B4 to classify cassava leaf diseases. Integrated into an Android app, it helps farmers detect diseases early, supporting sustainable farming and reducing crop losses.
RL-models-for-Super-Mario-Bros
This repository explores the application of three reinforcement learning algorithms—Deep Q-Networks (DQN), Double Deep Q-Networks (DDQN), and Proximal Policy Optimization (PPO)—for playing Super Mario Bros using the OpenAI Gym and nes-py emulator. It includes a comparative analysis of these models.
NLP-SoundSculptor
This project merges Natural Language Processing with music generation, using NLP techniques to analyze lyrics and guide the creation of music. It employs sentiment analysis, keyword extraction, and topic modeling, along with Genius and Spotify APIs, to generate music that reflects the emotional depth of the lyrics using the MusicGen model.
Autonomous-Kinect-Robot
An advanced robotics initiative harnessing Kinect's computer vision capabilities for precise object detection and manipulation, coupled with robust autonomous navigation and path planning technologies. Powered by an Arduino for seamless hardware control and real-time responsiveness.
travel-planner
Leveraging advanced AI to dynamically create personalized travel itineraries, this tool utilizes a Large Language Model, real-time web scraping, and Retrieval-Augmented Generation to adapt travel plans instantly based on user preferences and live data updates.
gym-super-mario-bros
An OpenAI Gym interface to Super Mario Bros. & Super Mario Bros. 2 (Lost Levels) on The NES
mit-deep-learning-book-pdf
MIT Deep Learning Book in PDF format (complete and parts) by Ian Goodfellow, Yoshua Bengio and Aaron Courville