Trending Projects

A curated list of robotics libraries and software for developers working on robotic applications.

A curated collection of resources for digital human modeling, avatar generation, and virtual try-on.

This repository contains code for comparing Generative Adversarial Networks (GANs), a type of machine learning model.

A Python-based Telegram bot that integrates with the ChatGPT language model, allowing users to interact with it through Telegram.

A configurable, tunable, and reproducible library for CTR prediction in Python with PyTorch support.

Open-source C++ library for high-quality depth estimation using the Semi-Global Matching algorithm, a classic and widely-used stereo matching algorithm.

Official code and checkpoint release for mobile robot foundation models like GNM, ViNT, and NoMaD.

Sample code for the Google Cloud Vision API, a powerful computer vision tool for image analysis.

Tools for causal analysis, helping developers understand and model causal relationships in their data.

An open-source computer vision library with thousands of pre-built algorithms and features.

UMAP is a dimension reduction library that can be used for visualization, exploration, and analysis of high-dimensional datasets.

A TypeScript library that uses AI to restore old and blurry face photos.

Shapash is a library that provides user-friendly explainability and interpretability for machine learning models.

An open-source language server that empowers software engineers with AI-powered functionality, not replacing them.

A library for semi-supervised learning on medical image segmentation tasks.

Open-source Python library for generating synthetic text images, useful for computer vision tasks.

An NCNN-based implementation of Real-ESRGAN, a practical algorithm for general image restoration and super-resolution.

A dataset of worldwide building footprints derived from satellite imagery for geospatial and computer vision applications.

A Rust library and CLI tool for extracting text from images using optical character recognition (OCR).

A curated list of awesome resources, tools, and other shiny things for LLM prompt engineering.

A desktop app that makes it easy to run Alpaca and other LLaMA-based local language models on your computer.

Real-time object recognition app built with TensorFlow and OpenCV for computer vision tasks.

A tiny Python library for coding with large language models (LLMs) like GPT-3 and ChatGPT.

A comprehensive survey on Meta AI's Segment Anything Model (SAM), a powerful computer vision tool.

A multimodal-driven architecture for customized video generation, enabling developers to create unique AI-powered videos.

End-to-end Chinese license plate recognition using MXNet, a machine learning framework.

A comprehensive framework for building enterprise-grade conversational AI experiences using Azure Bot Service and Bot Framework.

Real-time human pose estimation accelerated with NVIDIA TensorRT for efficient deployment on Jetson devices.

This book provides insights into interpretable machine learning techniques for developers.

Materials for the Hugging Face Diffusion Models Course, a resource for learning about diffusion models in AI.

An advanced multimodal AI model series for vision-language reasoning, developed by Skywork AI.

A TensorFlow-based implementation of Neural Style, a technique for applying the style of one image to the content of another.

A high-performance I/O system for large deep learning problems with strong PyTorch support.

Links to works on deep learning algorithms for physics problems, focused on TUM-I15 and beyond.

Open-source code for the ProteinMPNN paper, a machine learning model for protein structure prediction.

A real-time globally consistent 3D reconstruction library using online surface re-integration.

BASNet is a PyTorch library for boundary-aware salient object detection, useful for computer vision applications.

A concise machine learning cheatsheet covering the most popular algorithms.

Tools for training and deploying reinforcement learning models on the Unitree Go1 robot in a sim-to-real setting.

Forge is a neural network toolkit for Metal, enabling efficient deep learning on iOS devices.

Distribute and run AI workloads on Kubernetes with a Python-based infrastructure toolkit like PyTorch.

An open-source speech interaction system that integrates ASR, LLM, and TTS models for voice-based applications.

A Python library that provides a wrapper around various speech quality metrics for audio processing and analysis.

A highly optimized GPU-accelerated library for accelerating deep learning training and inference applications.

Benchmarks of approximate nearest neighbor libraries in Python for vibe coders building with AI tools.

This is a library for working with geometric deep learning algorithms, built by the Google DeepMind team.

An open-source cookbook for getting started with Phi, a family of high-performance small language models from Microsoft.

A large language model-powered virtual salesperson that can generate product descriptions to drive user purchases.

A Python library that uses GPT to parse and extract information from PDF documents.

An easy-to-use Python library for extracting information from documents using state-of-the-art AI models.