Skip to content
Catégories de projets

Apprentissage automatique · GitHub

Explorez les outils pour entraîner, évaluer et exécuter des modèles, et comparez leur popularité.

Projets GitHub utiles

12,806 projets

scirs

cool-japan

308étoiles

SciRS2 - Scientific Computing and AI in Rust., providing SciPy-compatible APIs while leveraging Rust's performance, safety, and concurrency features. Unlike traditional scientific libraries

  • GPU Acceleration with backend abstraction layer (CUDA, WebGPU, Metal)
  • Memory Management for large-scale computations
167étoiles
Awesome-Traffic-Prediction preview

Useful resources for traffic prediction, including popular papers, datasets, tutorials, toolkits, and other helpful repositories.

  • Deep Learning Based Traffic Prediction Methods
  • Curated Digest (Recent Years)

Geo-SAM

coolzhao

433étoiles
Geo-SAM preview

A QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster images.

STT

coqui-ai

2,604étoiles

🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so easy.

  • High-quality pre-trained STT model.
  • Efficient training pipeline with Multi-GPU support.
327étoiles

This page presents a list of satellite imagery datasets with a temporal dimension, mainly satellite image time series (SITS) and satellite videos, for various computer vision and deep learning tasks. It covers multi-temporal datasets with more than two acquisitions but not bi-temporal datasets.

async-rl

coreylynch

1,003étoiles
async-rl preview

Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"

OmniShow

Correr-Zhou

477étoiles
OmniShow preview

[ICML 2026] ByteDance's All-in-One Video Generation Model for Human-Object Interaction Video Generation

  • Multimodal Controllable Model: OmniShow is the first all-in-one model for Human-Object Interaction Video Generation (HOIVG) with text, reference image, audio, and pose conditioning.
  • Flexible Task Coverage: A single model supports R2V, RA2V, RP2V, and RAP2V generation within one coherent framework.

couler

couler-proj

944étoiles

Unified Interface for Constructing and Managing Workflows on different workflow engines, such as Argo Workflows, Tekton Pipelines, and Apache Airflow.

  • Simplicity and Extensibility: Couler provides a unified programming interface for workflow definition, ensuring independence from the workflow engine and compatibility with various workflow engines such as Argo Workflows, Airflow, and Tekton.
  • Automation: Couler integrates LLMs in unified programming code generation. By leveraging LLMs, Couler facilitates the generation of unified programming code using NL descriptions. Additionally, we automate hyperparameters tuning through the integration of Dataset Card and Model Card, enhancing the effectiveness of the autoML process.