Images to inference with no labeling (use foundation models to train supervised models).
- computer-vision
- model-distillation
- auto-labeling
- deep-learning
89,572 visible repositories in the index
1,561–1,584 of 5,041 · Most stars
Images to inference with no labeling (use foundation models to train supervised models).
Build a complete frontend in HTML
Open source implementation of Apple's Combine framework for processing values over time.
《机器翻译:基础与模型》肖桐 朱靖波 著 - Machine Translation: Foundations and Models
List of papers, code and experiments using deep learning for time series forecasting
A behavioral analytics library that uses dom mutations and user interactions to generate aggregated insights.
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台,我们欢迎开源爱好者发起任何有意义的pr!
Python tools for 3D face: 3DMM, Mesh processing(transform, camera, light, render), 3D face representations.
A CLI tool to query your local WeChat data — chat history, contacts, sessions, favorites, and more. Designed for LLM integration.
🔎 Impossibly fast web search, made for static sites.
Sampler, Sequencer, Multi-engine synth and effects - in a box! [WIP]
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Turn any Android device into a beautiful, dedicated Home Assistant kiosk. Purpose-built for Home Assistant from the ground up.
A self-hosted local image optimizer that runs in your browser.
Espressif IoT Library. IoT Device Drivers, Documentations and Solutions.
A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.
CV-CUDA™ is an open-source, GPU accelerated library for cloud-scale image processing and computer vision.
Plugin framework for CSS preprocessing in Node.js
Control Any Computer Using LLMs.
The Open Source Framework for Machine Vision
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
Multi-platform, free open source software for visualization and image computing.
Create a classic TV experience using your own media - IPTV backed by Plex/Jellyfin/Emby/NFO