Skip to content
Project categories

Machine Learning · GitHub

Train, evaluate, and run machine learning models.

Useful GitHub projects

12,832 projects

gaussctrl

ActiveVisionLab

136stars
gaussctrl preview

[ECCV 2024] GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing

Machine LearningPythonBSD-3-ClauseGitHub

DiT4SR

Adam-duan

276stars

[ICCV 2025] This is the official PyTorch codes for the paper: "DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution"

hamiltorch

AdamCobb

475stars

PyTorch-based library for Riemannian Manifold Hamiltonian Monte Carlo (RMHMC) and inference in Bayesian neural networks

Machine LearningJupyter NotebookBSD-2-ClauseGitHub

CapyMOA

adaptive-machine-learning

153stars
CapyMOA preview

CapyMOA does efficient machine learning for data streams in Python. CapyMOA is a toolbox of methods and evaluators for: classification, regression, clustering, anomaly detection, semi-supervised learning, online continual learning, and drift detection for data streams.

Machine LearningPythonBSD-3-ClauseGitHub

CEBRA

AdaptiveMotorControlLab

1,137stars

Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA

ProteinFlow

adaptyvbio

284stars

Versatile computational pipeline for processing protein structure data for deep learning applications.

Machine LearningPythonBSD-3-ClauseGitHub
42stars

'Primer to Machine Learning' is a comprehensive guide covering essential topics in machine learning, including statistics, data preprocessing, supervised and unsupervised learning, neural networks, deep learning, NLP, time series analysis, and reinforcement learning. Perfect for beginners and intermediates.

Machine LearningJupyter NotebookMITGitHub

CryptoBot

AdeelMufti

401stars

High(ish) frequency trading bot for cryptocurrencies, using Machine Learning for future price predictions

Machine LearningPythonApache-2.0GitHub
1,006stars

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.