Skip to content
Projektkategorien

Maschinelles Lernen · GitHub

Finde Frameworks zum Trainieren, Bewerten und Ausführen von Modellen und vergleiche das Community-Interesse.

Nützliche GitHub-Projekte

4,743 Projekte

sdnext

vladmandic

7,378Sterne+2in 24h
sdnext preview

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
286Sterne+2in 24h
modern-llm-notebook preview

A hands-on course on modern LLM architectures, training, and inference, with step-by-step PyTorch implementations and runnable notebooks.

webdataset

webdataset

3,219Sterne+2in 24h
webdataset preview

Ein leistungsstarkes, Python-basiertes E/A-System für große (und kleine) Deep-Learning-Probleme mit umfassender PyTorch-Unterstützung.

Maschinelles LernenPythonBSD-3-ClauseGitHub

Xsdsh-purge

xiaoshe1337-star

166Sterne+2in 24h
Xsdsh-purge preview

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

DIS

xuebinqin

2,591Sterne+2in 24h
DIS preview

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

Maschinelles LernenJupyter NotebookApache-2.0GitHub
9,724Sterne+2in 24h
video-subtitle-extractor preview

Grafisches Werkzeug und Deep-Learning-Framework zum Extrahieren fest ins Video eingebrannter Untertitel und Erstellen von SRT-Dateien. Es benötigt keine API eines Drittanbieters und führt die Texterkennung lokal aus. Es umfasst die Erkennung von Untertitelbereichen und die Extraktion der Untertitelinhalte.

QuantMuse

0xemmkty

2,988Sterne+1in 24h

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

1,718Sterne+1in 24h
OpenMLDB preview

OpenMLDB is an open-source machine learning database that provides a feature platform computing consistent features for training and inference.

mace

ACEsuit

1,412Sterne+1in 24h

MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.

1,007Sterne+1in 24h

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.

underPINN

Aeroscience-Computations-Analysis-Lab

39Sterne+1in 24h

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.

56,893Sterne+1in 24h
face_recognition preview

Die weltweit einfachste API zur Gesichtserkennung für Python und die Kommandozeile

  • Identify specific facial features in a photograph
  • Apply (horribly ugly) digital make-up
49Sterne+1in 24h
Plant-Disease-Classification preview

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

BloomBee

ai-decentralized

136Sterne+1in 24h

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.