Trending Projects

Code and models for Temporal Segment Networks (TSN) for action recognition in video understanding.

Converts any music library into a sample-library using machine learning techniques.

NICE-SLAM is a neural implicit approach for scalable 3D reconstruction and localization.

PyTorch extensions for fast R&D prototyping and Kaggle competition tools

A Python library for adding AI-powered image manipulation capabilities to the GIMP image editor.

PyQt5 implementation of YOLOv5 GUI for computer vision applications using AI tools.

MLeap is a library for deploying machine learning pipelines to production using Scala, Python, and Spark.

A Python toolkit to create optimal Production-ready Retrieval Augmented Generation (RAG) setups for AI/ML projects.

A video restoration transformer for deblurring, denoising, and super-resolution of videos.

A large-scale dataset of raw MRI measurements and clinical MRI images for medical imaging research.

A mock interview simulator with AI-powered feedback for developers to practice coding interviews.

A collection of camera mods to enhance the experience for developers using AI-powered tools.

Implementation of an alternative to backpropagation for training neural networks using PyTorch.

This repository provides implementations of different architectures for emotion recognition in conversations.

Code for a SIGGRAPH 2020 paper on neural rigging for articulated characters, likely useful for developers working on 3D animation and graphics.

A video conversation model that combines LLM capabilities with pretrained visual encoders for video-based chatbots.

A library of code samples and examples for deep learning and computer vision, targeting beginners.

Live Transcribe is an Android app that provides real-time captioning for people who are deaf or hard of hearing.

A flexible Python library for optical character recognition (OCR) using the CRAFT text detector and Keras CRNN recognition model.

A Graph Neural Network Library in Jax for building AI-powered graph-based applications.

High-performance N-dimensional tensor computation library for .NET, similar to NumPy for Python.

A framework for automated visual analytics, enabling developers to build AI-powered data visualization tools.

An open-source image annotation tool for computer vision tasks.

A PyTorch-based YOLOv4 and YOLOv5 implementation for detecting fire and smoke in images and videos.

PyTorch compiler that accelerates training and inference with built-in optimizations.

A JavaScript library for building reinforcement learning agents, covering various RL algorithms.

A PyTorch repository with various neural network models like CNN, BiLSTM, GRU, and LSTM for developers working with AI tools.

An implementation of federated learning, a distributed machine learning technique, using PyTorch.

Provides a collection of efficient and well-tested metric learning algorithms in Python for machine learning tasks.

Interface for OuteTTS models, a Python library for text-to-speech using transformer-based models.

An AI-powered application platform that simplifies and optimizes the development of large language model-based applications.

Object tracking implementation with YOLOv4, DeepSort, and TensorFlow for computer vision applications.

A flexible package for multimodal deep learning to combine tabular, text, and image data using Wide and Deep models in PyTorch.

Korean BERT pre-trained model for natural language processing tasks in the Korean language.

A collection of research papers on transformer models for computer vision tasks like detection and segmentation.

A starter kit to build local-only AI apps that cost $0 to run, focused on document Q&A.

A collection of open-source speech corpora for building speech recognition, synthesis, and other audio applications.

A Julia library for CUDA programming, enabling high-performance GPU computing on a wide range of NVIDIA hardware.

This repository contains the author's winning solutions for various data science competitions, serving as a valuable resource for vibe coders.

A simple facial recognition API for .NET that works on Windows, macOS, and Linux with support for various ML tasks.

Offline OCR SDK for Chinese text detection and recognition, built with deep learning and transformer models.

ChatReviewer uses ChatGPT to analyze research papers and provide improvement suggestions for developers.

An open-source framework for building knowledgeable large language models with fine-tuning capabilities.

A comprehensive solution to deploy a multi-LLM and multi-RAG powered chatbot using AWS CDK on AWS.

A Jupyter Notebook project that converts PDF documents to audio using AI-powered text-to-speech.

A library that helps developers train BERT-type language models with limited compute resources.

Supporting code for a short YouTube series on demystifying neural networks.

A powerful conversational AI JavaScript library that supports various LLM providers and integrates with UI frameworks.

UNO is a universal customization method for both single and multi-subject image generation using diffusion models.

BSRGAN is a PyTorch library for designing practical degradation models for deep blind image super-resolution.