Trending Projects

An IBM toolkit for computing on encrypted data without decryption, with demos for secure ML and key-value search.

Slides and Jupyter notebooks for deep learning lectures at a Master's program in data science.

JoJoGAN is a PyTorch-based library for one-shot face stylization, enabling developers to create anime-style portraits.

A pure Java speech recognition library that can be used in various applications.

An open-source Chinese AI dungeon game that uses the OpenAI ChatGPT API for storytelling.

Differentiable data augmentation techniques for efficient training of generative adversarial networks (GANs).

A Python toolbox to investigate neural networks' predictions and understand model behavior.

A Python-based tool that allows customizing the 'cutoff' effect in Stable Diffusion, a popular AI-powered image generation model.

A Chinese spell checker tool built with Python for correcting spelling mistakes in Chinese text.

A comprehensive Python and C++ data mining library for algorithms, clustering, neural networks, and more.

A neural question generation model built using transformers for generating high-quality questions from text.

A Jupyter Notebook project that explores techniques for reconstructing images from Stable Diffusion models.

A single-header-only modern ray tracing kernel for vibe coders building AI-powered graphics apps.

The final version of an AI-designed keyboard layout, written in C, for vibe coders.

This repository provides projects for monocular depth estimation and 3D scene reconstruction from single images.

A C++ library for 3D mapping and segmentation, potentially useful for robotics and computer vision applications.

This repository contains a CVPR2024 paper on referring human dance generation using AI tools.

A deep learning library for generating and manipulating images, including semantic style transfer.

A PyTorch implementation of the Efficient Neural Architecture Search (ENAS) algorithm for AI model optimization.

Interactive Go programming with Jupyter, enabling data science and machine learning workflows.

API libraries, samples, and system images for building AI-powered devices using Raspberry Pi and Python.

An open library of computer vision algorithms written in C.

A modular, extensible framework for building AI-powered agents and bots using the GPT language model.

An open-source tool for quickly annotating and labeling images for computer vision and deep learning projects.

Pre-trained Chinese ELECTRA language model for natural language processing tasks.

An open-source library for research on learning disentangled representations.

Personae is a repo for implementing and experimenting with Deep Reinforcement Learning and Supervised Learning for Quantitative Trading.

A C++ library for facial recognition and detection in ROS (Robot Operating System) applications.

speak.js is a text-to-speech library for JavaScript that uses the eSpeak speech synthesis engine.

A PyTorch-based library for named entity recognition using the BERT language model.

PaddleViT is a state-of-the-art Visual Transformer and MLP model library for the PaddlePaddle 2.0+ deep learning framework.

A curated list of resources for relation extraction, a key NLP task, useful for vibe coders.

An endless procedurally generated acid banger music generation tool built with TypeScript.

A PyTorch implementation of StyleGAN for domain adaptation, using pre-trained models to generate new images.

A TensorFlow library for learning distributed representations of code using the code2vec neural network model.

A TensorFlow implementation of DeepMind's WaveNet paper for generating high-quality speech audio.

Edward is a probabilistic programming language in TensorFlow for deep generative models and variational inference.

A fork of the Tesseract Tools for Android library, which provides OCR functionality.

This is a best practice for a TensorFlow project template architecture for developers building AI-powered applications.

A library of semantic segmentation architectures implemented in PyTorch for computer vision applications.

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

A Python library for building question-answering systems on top of Notion data.

A C++ library that estimates the psychovisual difference between two images, useful for image processing and quality assessment.

A PyTorch toolkit for training and evaluating LSTM and QRNN language models.

An all-in-one solution for adding Temporal Stability to Stable Diffusion models using an Automatic1111 extension.

A must-have resource for experimenting with and building on the OpenAI vision API.

A deep reinforcement learning library for developing AI agents using neuroevolution.

Multimodal-GPT is a powerful library for building AI-powered applications that leverage multimodal data like text, images, and more.

A collaboration workspace for Machine Learning, supporting popular ML frameworks and enabling reproducible workflows.

A deep learning toolkit for medical image analysis, supporting a variety of neural network models and medical imaging tasks.