Trending Projects

A C# library that provides a realtime interface to the Automatic1111 Stable Diffusion API for AI-powered image generation.

A curated list of awesome AI, ML, and DL resources, including code, tutorials, and study notes.

Rinha de Backend is a Lua-based backend framework and development platform for building AI-powered applications.

A lightweight Python library that provides a unified API for common reranking and cross-encoder models.

Official implementation of a paper on a unified Transformer-based framework for object detection and segmentation.

Advanced toolkit for medical image registration, segmentation, and processing, with a focus on neuroimaging.

A high-performance C++ library for neural machine translation, with CUDA support for GPU acceleration.

DataComp for Language Models is a library for training, evaluating, and deploying large language models.

OpenXuantie - OpenC910 Core is a Verilog-based hardware design for the RISC-V C910 core, targeted at AI and ML workloads.

This repository provides a technical introduction to common neural network architectures like feedforward, convolutional, and recurrent networks.

A highly accurate deep learning-based license plate detection and recognition system for real-time use.

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

A flexible and powerful monitoring system for vibe coders to monitor their AI-powered applications.

Official implementation of a paper on estimating geometry in the presence of motion, likely useful for computer vision and 3D applications.

A speech emotion recognition library implemented in Keras with support for CNN, LSTM, SVM, and MLP models.

E2M is a flexible, open-source tool that converts various file types to Markdown, making it easy for vibe coders to work with content.

An all-in-one tool for AI-powered song cover creation, including YouTube audio download, vocal separation, audio splitting, training, and inference.

A tooling repository for the Common Objects In 3D dataset, focused on 3D object reconstruction and detection.

A curated list of papers related to imbalance problems in object detection research.

Attention-based OCR library for building vision AI apps that extract text from images.

Official PyTorch implementation of a prompt-based distillation method for on-device deployment of the Segment Anything Model (SAM).

Flutter development tools for vibe coders

A Python library that empowers developers to build applications and systems with self-contained computer vision capabilities.

Real-time high-resolution background matting tool for computer vision and ML applications.

A Chinese translation of the book 'Hands-On Machine Learning with Scikit-Learn and TensorFlow' for developers interested in machine learning and AI tools.

A distributed deep learning platform for building and deploying AI models at scale.

A Java-based AI constraint solver for optimizing vehicle routing, employee rostering, and other planning problems.

A Python library that uses AnimeGANv3 to convert photos or videos into anime-style art.

A collection of PyTorch tutorials from a YouTube channel, focusing on machine learning and deep learning.

A no-code AutoML tool that generates a working model from a CSV file and target field.

NeuS is a Python library for neural surface reconstruction, a key component in 3D computer vision.

A Python library for using large language models (LLMs) as powerful text encoders for downstream NLP tasks.

An official paper from CVPR 2024 on a talking head synthesis model that focuses on audio-driven synchronization.

This open-source repository provides a collection of state-of-the-art visual object tracking algorithms built with PyTorch for developers working on computer vision and deep learning projects.

Open-source implementations of machine learning algorithms from scratch in Python.

A fast symbolic computation library for robotics, with capabilities like code generation and nonlinear optimization.

A collection of edge/contour/boundary detection papers and toolbox for computer vision tasks.

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

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

A comprehensive repository of 1000+ AI algorithm interview questions across 25 categories for vibe coders.

A PyTorch implementation of a voice separation algorithm for mixed audio with multiple speakers.

A JavaScript library for developing game AI, focused on creating intelligent and engaging game characters.

A curated list of must-read papers on knowledge editing for large language models.

A collection of high-quality open-source speech, audio, and codec models for building AI-powered speech applications.

A multimodal framework for drug discovery and therapeutic science research.

An AI-powered tool for anime image inpainting and restoration, useful for computer vision and generative art projects.

A nightly release of the ControlNet library, a powerful tool for controlling the outputs of AI models.

A modular Stable Diffusion web UI with a focus on making AI tools easily accessible and extensible.

A Tensorflow solution for Named Entity Recognition (NER) using the BERT-BiLSTM-CRF model with BERT fine-tuning.

A comprehensive list of recommender systems and related resources for developers.