训练框架

💁 Awesome Treasure of Transformers Models for Natural Language processing contains papers, videos, blogs, official repo along with colab Notebooks. 🛫☑️

🌝 MLKit是一个强大易用的工具包。通过ML Kit您可以很轻松的实现文字识别、条码识别、图像标记、人脸检测、对象检测等功能。

ONNXMLTools enables conversion of models to ONNX

Tools for handling multimodal data in machine learning projects.

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

🔥 An autonomous AI agent that runs your deep learning experiments 24/7 while you sleep. Zero-cost monitoring, Leader-Worker architecture, constant-size memory.

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

Z80-μLM is a 2-bit quantized language model small enough to run on an 8-bit Z80 processor. Train conversational models in Python, export them as CP/M .COM binaries, and chat with your vintage computer.

Samples and Tools for Windows ML.

Microsoft AI for Good Lab — Biodiversity research hub. Open-source AI models, edge devices, and tools for biodiversity monitoring and conservation. Your source for MegaDetector, SPARROW, PytorchWildlife, Bioacoustics, and more.

RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.

Efficient Deep Learning Systems course materials

[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation

LibreYOLO is a MIT licensed open source computer vision library

A tool for converting ONNX files to LiteRT/TFLite/TensorFlow, PyTorch native code (nn.Module), TorchScript (.pt), state_dict (.pt), Exported Program (.pt2), and Dynamo ONNX. It also supports direct conversion from LiteRT to PyTorch.

Jetson Nano with Ubuntu 20.04 image

Resource, examples & tutorials for multimodal AI, RAG and agents using vector search and LLMs

Official implementation of Half-Quadratic Quantization (HQQ)

Code for 3D object detection for autonomous driving

A scalable inference server for models optimized with OpenVINO™

Python toolkit, MCP server, and agent skills for reproducible, auditable clickstream and event log analytics. Helps AI agents, data scientists and analysts build, validate, and cross-check product analytics, quantitative UX, customer journeys, graph-based user flows, behavioral segmentation, A/B tests, process mining models, Markov chain simulation

[ICLR 2024] Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention

Data compression in TensorFlow

MindSpore + 🤗Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless compatibility and acceleration.

MONAI Label is an intelligent open source image labeling and learning tool.

A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine

cuVS - a library for vector search and clustering on the GPU

[CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

[CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

Python Computer Vision & Video Analytics Framework With Batteries Included

:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler

Darknet/YOLO object detection framework

LLVIP: A Visible-infrared Paired Dataset for Low-light Vision

DIPY is the paragon 3D/4D+ medical imaging library in Python. Contains generic methods for spatial normalization, signal processing, machine learning, statistical analysis and visualization of medical images. Additionally, it contains specialized methods for computational anatomy including diffusion, perfusion and structural imaging.

DeepInverse: a PyTorch library for solving imaging inverse problems using deep learning

自动驾驶笔记，以解析各模块知识点、整合行业优秀解决方案进行阐述，以帮助自己及有需要的读者；包含深度学习、deeplearning、无人驾驶、BEV、Transformer、ADAS、CVPR、特斯拉AI DAY、大模型、chatgpt等内容.

A Graph RAG System for Evidenced-based Medical Information Retrieval [ACL 2025]

Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/

List of Deep Learning Cloud Providers

High-performance Vision library in Python. Scale your research, not boilerplate.

[TMLR 2025🔥] A survey for the autoregressive models in vision.

A Python high-performance screen capture library for Windows using Desktop Duplication API - Updated 2026

Machine learning framework for both deep learning and traditional algorithms

CnSTD: 基于 PyTorch/MXNet 的 中文/英文 场景文字检测（Scene Text Detection）、数学公式检测（Mathematical Formula Detection, MFD）、篇章分析（Layout Analysis）的Python3 包

Deep learning for audio processing

AI Productivity Tool - Free and open source, improve user productivity, and protect privacy and data security. Including but not limited to: built-in local exclusive ChatGPT, DeepSeek, Phi, Qwen and other models, one-click batch intelligent processing of pictures, videos, audio, etc.

Learn how to create, develop, and maintain a state-of-the-art MLOps code base

YOLOv8 TensorRT C++ Implementation