Trending Projects

Official PyTorch implementation of the SinGAN paper, a generative model that can be trained on a single natural image.

An official repository for the 'Mini-Gemini' model, a multi-modal vision-language model for generation tasks.

A Python-based service that allows developers to use large language models (LLMs) as a chatbot backend.

A convertor/conversion tool for deep learning models across various deep learning frameworks/software.

InternGPT is an open-source demo platform that showcases various AI models, including DragGAN, ChatGPT, ImageBind, and multimodal chat.

An open-source Chinese NLP library providing state-of-the-art tools for word segmentation, dependency parsing, named entity recognition, and more.

Organized resources for deep learning researchers and developers, including tutorials, frameworks, and libraries.

A Keras library for building sequence-to-sequence models, useful for vibe coders building AI-powered apps.

A simplified interface for TensorFlow that mimics Scikit Learn for building deep learning models.

TensorFlow API for .NET languages, enabling .NET developers to build machine learning models.

Pretrained language model and optimization techniques for large-scale distributed AI/ML development.

A Python library for face swapping, part of the deepfakes community.

TensorFlow Reinforcement Learning library for developing AI agents and models.

A Python wrapper for the MuJoCo physics engine, enabling detailed rigid body simulations with contacts.

Open-source pre-training model framework in PyTorch with a pre-trained model zoo for natural language processing tasks.

An unofficial PyTorch implementation of the audio LM VALL-E, a text-to-speech AI model.

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model

Example TensorFlow codes and a TensorFlow as a Service dev environment for AI/ML developers.

An open autoregressive foundational video AI model for vibe coders building with AI tools.

High-performance vector graph neural network database in Rust for real-time AI inference and graph ML.

A survey and analysis of various large language model (LLM) agents and their capabilities.

This repository contains deep learning-based articles, papers, and repositories for recommendation systems.

AI-powered manga translator with OCR & bubble detection for Japanese comics to Chinese

Official Python SDK for Claude API—LLM wrapper for building AI apps with Anthropic's models

Swift SDK for OpenAI API integration with type-safe wrappers and modern concurrency support.

A MATLAB library for joint face detection and alignment using multi-task cascaded convolutional neural networks.

A JavaScript computer vision library with a wide range of computer vision algorithms.

A distributed machine learning toolkit from Microsoft for building scalable AI and ML models.

A curated list of resources for Learning with Noisy Labels, focusing on robust deep learning models.

Windows desktop front end for the Spleeter AI source separation library, enabling developers to easily separate audio files.

A collection of machine learning tools in JavaScript for developers to build AI-powered applications.

LSD-SLAM is a real-time monocular SLAM (Simultaneous Localization and Mapping) algorithm written in C++.

MUNIT is a deep learning-based method for multimodal unsupervised image-to-image translation, enabling vibe coders to create diverse and stylized images.

Propel is a differentiable programming library that allows developers to build AI-powered applications in JavaScript.

A fast, easy, and collaborative open-source image annotation tool for teams and individuals.

Resource scheduling and cluster management for AI workloads on Kubernetes and other platforms.

A PyTorch optimizer that adapts the learning rate to reduce the variance of gradients, improving training performance.

A PyTorch library for face parsing using a modified BiSeNet model, useful for computer vision and image processing tasks.

Benchmarks for popular CNN models, useful for developers working on computer vision and deep learning projects.

A TensorFlow implementation of the Differentiable Neural Computer, a powerful AI tool for vibe coders.

A PyTorch implementation of a Convolutional Recurrent Network for scene text recognition.

Elegant PyTorch implementation of the Model-Agnostic Meta-Learning (MAML) paper for AI/ML developers.

Efficient Segment Anything, a leveraged masked image pretraining model for efficient segmentation.

A Keras implementation of CapsNet, a deep learning model for image classification.

Dual Attention Network for Scene Segmentation, a computer vision model for image segmentation.

An Android app for the open-source SUSI.AI AI assistant, providing voice-based interaction and information.

A set of learning notes for the Apollo autonomous driving framework, useful for developers building self-driving car systems.

A framework for integrated Artificial Intelligence & Artificial General Intelligence (AGI)

An open-source multi-modal AI model based on LLaMA-3.8B for vibe coders to build with AI tools.

An open-source library for contrastive representation distillation, a knowledge distillation technique.