Skip to content
Project categories

Machine Learning · GitHub

Train, evaluate, and run machine learning models.

Useful GitHub projects

12,806 projects

ProtoPNet

cfchen-duke

427stars

This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpretable Image Recognition" (to appear at NeurIPS 2019), by Chaofan Chen* (Duke University), Oscar Li* (Duke University), Chaofan Tao (Duke University), Alina Jade Barnett (Duke University), Jonathan Su (MIT Lincoln Laboratory), and Cynthia Rudin (Duke University) (* denotes equal contribution).

CFGpp

CFGpp-diffusion

244stars
CFGpp preview

Official repository for "CFG++: manifold-constrained classifier free guidance for diffusion models" (ICLR2025)

rnaglib

cgoliver

46stars
rnaglib preview

Toolkit for structure-based deep learning on RNA.

  • Benchmark ML models
  • Fetch and browse annotated RNA 3D structures
38stars
neural-trees preview

sklearn-compatible PyTorch implementations of Soft Decision Trees, HMoE, and classifier comparison tests (5×2cv F-test). pip install neural-trees

  • scikit-learn compatible API (fit, predict, score, works in Pipeline)
  • PyTorch backend with GPU support (device="auto" picks CUDA, then Apple silicon MPS, then CPU)
210stars

A complete example of a big data application using : Kubernetes (kops/aws), Apache Spark SQL/Streaming/MLib, Apache Flink, Scala, Python, Apache Kafka, Apache Hbase, Apache Parquet, Apache Avro, Apache Storm, Twitter Api, MongoDB, NodeJS, Angular, GraphQL

Machine LearningTypeScriptApache-2.0GitHub

spandrel

chaiNNer-org

317stars

Spandrel gives your project support for various PyTorch architectures meant for AI Super-Resolution, restoration, and inpainting. Based on the model support implemented in chaiNNer.

526stars

Geometric GNN Dojo provides unified implementations and experiments to explore the design space of Geometric Graph Neural Networks (ICML 2023)

Machine LearningJupyter NotebookMITGitHub
323stars
geometric-rna-design preview

gRNAde is a Generative AI framework for inverse design of 3D RNA structure and function

  • 3D RNA Design: Conditions on 3D coordinates to capture non-canonical pairings and tertiary motifs that 2D-only methods miss. Supports multi-modal design specifications including pseudoknotted secondary structures, 3D backbones, and partial sequence constraints (e.g., from fitness landscapes)
  • Expert-Level Accuracy on Pseudoknots: Matches human expert performance on the Eterna OpenKnot Benchmark while being fully automated.
Machine LearningJupyter NotebookMITGitHub

seqeval

chakki-works

1,188stars

A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)

  • IOBES(only in strict mode)
  • BILOU(only in strict mode)