3,646星标+224小时
“数学不难”之《线性代数不难》上下册，66 话题完册；欢迎批评指正。
机器学习 · GitHub
发现模型训练、评估与推理框架，比较深度学习和机器学习项目的社区关注度。
实用 GitHub 项目
4,743 个项目
sdnext
vladmandic
7,378星标+224小时
SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing
- Generate and edit: Create images or videos from text or images; edit, inpaint, outpaint, refine, detail
- Guide generation: Use LoRA, ControlNet, IP-Adapters, and Prompt enhancement
modern-llm-notebook
walkinglabs
286星标+224小时
A hands-on course on modern LLM architectures, training, and inference, with step-by-step PyTorch implementations and runnable notebooks.
webdataset
webdataset
3,219星标+224小时
面向大规模（也支持小规模）深度学习任务的高性能 Python I/O 系统，为 PyTorch 提供强大支持。
Xsdsh-purge
xiaoshe1337-star
166星标+224小时
沿用了此项目：https://github.com/YuJunZhiXue/dsh-purge 专注于deepseek harness破甲|逆向|渗透| 适配最新版deepseek harness ：deepseek v4.1 flash 最新版 更新q群562341656
projectlearn-project-based-learning
Xtremilicious
6,400星标+224小时
一份面向项目式学习的精选项目教程列表。
DIS
xuebinqin
2,591星标+224小时
This is the repo for our new project Highly Accurate Dichotomous Image Segmentation
ml-road
yanshengjia
4,982星标+224小时
机器学习与智能体 AI 资源、实践和研究
video-subtitle-extractor
YaoFANGUK
9,724星标+224小时
一款用于提取视频硬字幕并生成 SRT 文件的图形界面工具和深度学习框架。无需申请第三方 API，可在本地进行文本识别。框架包含字幕区域检测和字幕内容提取。
QuantMuse
0xemmkty
2,988星标+124小时
A comprehensive quantitative trading system with AI-powered analysis, real-time data processing, and advanced risk management
- 🔬 Advanced Factor Analysis: Multi-factor models with momentum, value, quality, and volatility factors
- 🤖 AI/LLM Integration: OpenAI GPT integration for market analysis and strategy recommendations
OpenMLDB
4paradigm
1,718星标+124小时
OpenMLDB is an open-source machine learning database that provides a feature platform computing consistent features for training and inference.
pytorch-nested-unet
4uiiurz1
1,056星标+124小时
PyTorch implementation of UNet++ (Nested U-Net).
approachingalmost
abhishekkrthakur
8,409星标+124小时
Approaching (Almost) Any Machine Learning Problem
mace
ACEsuit
1,412星标+124小时
MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.
adapters
adapter-hub
2,833星标+124小时
A Unified Library for Parameter-Efficient and Modular Transfer Learning
Machine-Learning-Links-And-Lessons-Learned
adeshpande3
1,007星标+124小时
List of all the lessons learned, best practices, and links from my time studying machine learning
- It's also model dependent. Normalization will likely help for linear models like linear/logistic reg, but won't be as helpful for deep learning models and neural networks.
- In order to determine whether it will help or not, visualize your data to see what type of features you're dealing with. Do you have some features that have values around 1000 or 2000? Do you have some that are only 0.1 or 0.2? If so, normalizing those inputs is likely a good idea.
multi-object-tracker
adipandas
698星标+124小时
Multi-object trackers in Python
underPINN
Aeroscience-Computations-Analysis-Lab
39星标+124小时
A modular, JAX-based framework for Physics-Informed Neural Networks, designed for scalable PDE-constrained learning with support for domain decomposition, attention mechanisms, and performance-oriented training.
face_recognition
ageitgey
56,893星标+124小时
全球最简单的 Python 和命令行人脸识别 API
- Identify specific facial features in a photograph
- Apply (horribly ugly) digital make-up
Plant-Disease-Classification
AhmadJeddi
49星标+124小时
A ResNet50-DCBAM deep learning framework for plant disease classification using the PlantVillage dataset with reproducible training and evaluation pipelines.
- ResNet50 backbone with pretrained ImageNet weights
- Channel attention
From-0-to-Research-Scientist-resources-guide
ahmedbahaaeldin
7,693星标+124小时
Detailed and tailored guide for undergraduate students or anybody want to dig deep into the field of AI with solid foundation.
awesome-robotics
ahundt
1,525星标+124小时
A curated list of awesome links and software libraries that are useful for robots.
BloomBee
ai-decentralized
136星标+124小时
Decentralized LLMs fine-tuning and inference with offloading
- Tensor offloading — reduces per-node memory consumption so each peer can host more layers, shrinking the total number of network hops.
- Speculative decoding over internet — reduces communication frequency by sending multiple draft tokens per round-trip.
304星标+124小时
Master AI inference, AI agent harness systems, and hardware engineering — then design a physical AI chip. That is the goal.