Skip to content
Project categories

Machine Learning · GitHub

Train, evaluate, and run machine learning models.

Useful GitHub projects

12,804 projects

rnnlib

szcom

902stars

RNNLIB is a recurrent neural network library for sequence learning problems. Forked from Alex Graves work http://sourceforge.net/projects/rnnl/

benchm-ml

szilard

1,894stars
benchm-ml preview

A minimal benchmark for scalability, speed and accuracy of commonly used open source implementations (R packages, Python scikit-learn, H2O, xgboost, Spark MLlib etc.) of the top machine learning algorithms for binary classification (random forests, gradient boosted trees, deep neural networks etc.).

MEAL-V2

szq0214

698stars
MEAL-V2 preview

MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.

26stars
deepstack-trainer preview

FastAPI web app to train and test a DeepStack AI server: register faces, and test face recognition, object detection and scene detection

  • Face registration (learning) - upload a photo and a person's name to register the face with DeepStack.
  • Face recognition test - upload a photo and see which registered people DeepStack recognizes in it.

TransFG

TACJu

422stars

This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).

AvatarForcing

TaekyungKi

370stars

[CVPR 2026] Official Pytorch implementation of Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation

333stars

Official Pytorch implementation of "Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment (ECCV 2022)"

ppo-rocket-landing

taherfattahi

244stars
ppo-rocket-landing preview

Proximal Policy Optimization (PPO) algorithm using PyTorch to train an agent for a rocket landing task in a custom environment

  • Custom Rocket Environment: Simulates rocket physics for hovering and landing tasks.
  • PPO Algorithm Implementation: Utilizes both actor and critic neural networks for policy optimization.

MeshSegNet

Tai-Hsien

335stars
MeshSegNet preview

PyTorch version of MeshSegNet for tooth segmentation of intraoral scans (point cloud/mesh). The code also includes visdom for training visualization; this project is partially powered by SOVE Inc.