Trending Projects

A Python library that helps prevent CUDA out of memory errors in PyTorch models with just 1 line of code.

A collection of state-of-the-art deep learning scripts for various AI/ML tasks, easily trainable and deployable.

Open-source machine learning compiler framework for building and optimizing AI models across a variety of hardware.

A collection of tutorials and notebooks on state-of-the-art computer vision models and techniques for developers.

Inference and training library for high-quality text-to-speech (TTS) models.

OneTrainer is a comprehensive solution for training Diffusion models, including fine-tuning, LORA, and more.

A timeline of the latest AI models for audio generation, starting in 2023.

This GitHub repository hosts the open-source organization ApacheCN, which focuses on AI, ML, and data science tools and resources.

An MXNet implementation of Mask R-CNN, a deep learning object detection and segmentation algorithm.

A PyTorch-dedicated tensor container for vibe coders building with AI tools.

Open R1 is a fully open reproduction of DeepSeek-R1, enabling replication and extension of its reasoning capabilities.

A library of deep learning models and datasets to make deep learning more accessible and accelerate ML research.

A companion website to the book 'Mathematics For Machine Learning'.

An open-source toolkit for speech processing, supporting enhancement, separation, and target speaker extraction.

A collection of resources related to event-based vision technology, including papers, workshops, datasets, and code.

A Python tool that allows users to edit images generated by the Stable Diffusion AI model

A deep learning-based tool for separating vocals from audio signals, useful for music production and audio processing.

Official PyTorch implementation of TokenFlow, a novel diffusion-based method for consistent video editing presented at ICLR 2024.

A deep learning library for head pose estimation using PyTorch, useful for computer vision applications.

TerraBrush is a C++ library for procedural terrain generation, providing tools for vibe coders to create dynamic and realistic environments.

LocalGPT enables private document interaction with GPT models on your device.

Recommenders is a project for prototyping and operationalizing recommendation systems with Jupyter notebooks and best practices.

Bob is a macOS app that provides translation and OCR capabilities for developers who work with AI tools.

pytesseract is a Python wrapper for Google Tesseract, a popular optical character recognition (OCR) engine.

DeepSeek-V2 is a powerful, efficient, and economical mixture-of-experts language model for vibe coders building with AI tools.

An engine-agnostic deep learning framework in Java that supports popular AI/ML runtimes like TensorFlow, PyTorch, and ONNX.

A comprehensive resource for industrial image anomaly/defect detection papers and datasets.

GLIGEN is an open-source library for grounded text-to-image generation, enabling developers to create AI-powered image generation models.

A Python library for physical symbolic optimization, combining deep learning and reinforcement learning.

A comprehensive collection of tools, papers, and code for detecting deepfake media.

VeOmni is a scalable distributed training framework for multi-modal AI models, focused on vibe coders.

Extensible, parallel implementations of the popular t-SNE dimensionality reduction algorithm for data visualization.

A benchmark for evaluating knowledge transfer in lifelong robot learning using AI tools.

Official repository of a book on deep learning with PyTorch, a popular machine learning framework.

This is an EPFL course on optimization for machine learning, focused on Jupyter Notebook usage.

A real-time text-to-speech model that can stream conversational audio in real-time.

Official implementation of the ADBench anomaly detection benchmark for machine learning models

An open-source implementation of the AlphaCodium paper, enabling AI-powered code generation and flow engineering for developers.

A comprehensive collection of resources and techniques for advanced prompt engineering with large language models like ChatGPT.

An open-source neural hierarchical multi-label text classification toolkit for AI and NLP applications.

Add AI-powered image upscaling to SteamVR games using AMD FidelityFX SuperResolution or NVIDIA Image Scaling.

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

A tool for creating comics using AI, supporting script writing, storyboarding, and character style control.

A Python library for training deep neural networks with weights and activations constrained to +1 or -1.

A Python project that generates realistic-sounding text using a pre-trained GPT-2 model, useful for AI coding tools and language generation.

Open3D is a modern C++ library for 3D data processing, including reconstruction, registration, and visualization.

A curated list of papers and resources focused on 3D Gaussian Splatting, a technique used in neural rendering.

ESRGAN is a super-resolution AI model that can upscale images with high perceptual quality.

A natural language modeling framework based on PyTorch for building AI-powered applications.

The official Go library for the OpenAI API, enabling developers to integrate AI capabilities into their applications.