AI 开源项目榜。

Reference implementations of MLPerf® training benchmarks

The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

Notes on the Deep Learning book from Ian Goodfellow, Yoshua Bengio and Aaron Courville (2016)

SECOND for KITTI/NuScenes object detection

A complete video subtitle editing React component with AI-powered speech recognition and visual editing capabilities.

AI-native software testing platform — one YAML test language covering API, Web, mobile, messaging, data, and LLM scenarios. Self-hostable.

Emu Series: Generative Multimodal Models from BAAI

High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime

Top 200 deep learning Github repositories sorted by the number of stars.

Caption-Anything is a versatile tool combining image segmentation, visual captioning, and ChatGPT, generating tailored captions with diverse controls for user preferences. https://huggingface.co/spaces/TencentARC/Caption-Anything https://huggingface.co/spaces/VIPLab/Caption-Anything

Try out deep learning models online on Google Colab

PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

彙整了真正實用的 ChatGPT 與生成式 AI 工具

Gemini auth plugin for opencode

The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

自然语言处理、知识图谱、大语言模型，Agent等技术的前沿追踪、研究与应用。

A native macOS AI chat app powered by MLX. 100% local inference on Apple Silicon, no cloud required. Built with ShipSwift.

Generate your Twitter bio with AI

OpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It significantly enhances code generation capabilities by integrating execution and iterative refinement functionalities.

Vision utilities for web interaction agents 👀

License Plate Detection and Recognition in Unconstrained Scenarios

"Multi-Level Intermediate Representation" Compiler Infrastructure

novel deep learning research works with PaddlePaddle

A domain specific language to express machine learning workloads.

Speedy Wavenet generation using dynamic programming :zap:

A Modular Framework for 3D Gaussian Splatting and Beyond

Fuel your productivity with ChatGPT-Desktop - Blazingly fast and supercharged!

ESP32 Camera motion capture application to record JPEGs to SD card as AVI files and stream to browser as MJPEG. If a microphone is installed then a WAV file is also created. Files can be uploaded via FTP or downloaded to browser.

Pytorch-based tools for visualizing and understanding the neurons of a GAN. https://gandissect.csail.mit.edu/

AIdea 是一款支持 GPT 以及国产大语言模型通义千问、文心一言等，支持 Stable Diffusion 文生图、图生图、 SDXL1.0、超分辨率、图片上色的全能型 APP。