Skip to content
Project categories

Machine Learning · GitHub

Train, evaluate, and run machine learning models.

Useful GitHub projects

12,832 projects

MegaDetector

agentmorris

349stars
MegaDetector preview

MegaDetector is an AI model that helps conservation folks spend less time doing boring things with camera trap images.

25,600stars
handson-ml preview

⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 or handson-mlp instead.

Machine LearningJupyter NotebookApache-2.0GitHub

xuance

agi-brain

1,114stars
xuance preview

XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library

  • :school_satchel: Highly modularized.
  • :thumbsup: Easy to learn, easy for installation, and easy for usage.

covalent

AgnostiqHQ

869stars
covalent preview

Pythonic tool for orchestrating machine-learning/high performance/quantum-computing workflows in heterogeneous compute environments.

Machine LearningPythonApache-2.0GitHub

sgan

agrimgupta92

921stars
sgan preview

Code for "Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks", Gupta et al, CVPR 2018

AgriQuant-AI

AgriQuantAI

580stars

AI-powered weather intelligence for agricultural commodity futures. Predicts price moves 48-72 hours early across OJ, Coffee, Cocoa, Sugar, Corn and Wheat using Claude Sonnet + satellite data

221stars

This series uncovers the most valuable insights from groundbreaking books in AI, Machine Learning, and Data Science, helping you accelerate your learning journey. Each episode transforms complex theories into practical knowledge, making advanced topics more accessible and actionable.

50stars
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

Resnet-DCBAM

AhmadJeddi

44stars

A clean and modular PyTorch implementation of DCBAM (Dual-Channel & Spatial Attention) integrated into a custom ResNet50 backbone. Includes attention modules, pretrained weight loading, layer freezing, full examples, and production-ready architecture.