Skip to content
Categorías de proyectos

Aprendizaje automático · GitHub

Explora herramientas para entrenar, evaluar y ejecutar modelos, y compara el interés de la comunidad.

Proyectos útiles de GitHub

4,743 proyectos

visdom

fossasia

10,343estrellas+2in 24h
visdom preview

Tool for real-time visualization, monitoring and collaborative analysis of AI/ML experiments and live data. Supports Python, PyTorch/Torch, NumPy, TensorFlow/Keras https://visdom.dev

Aprendizaje automáticoPythonApache-2.0GitHub

Girls-In-AI

girls-in-ai

3,426estrellas+2in 24h
Girls-In-AI preview

免费学代码系列：小白python入门、数据分析data analyst、机器学习machine learning、深度学习deep learning、kaggle实战

Aprendizaje automáticoJupyter NotebookGitHub

TartarusSolver

glcoder

57estrellas+2in 24h

Ofrece indicaciones de movimiento para Tartarus Prison, en Torchlight: Infinite. Una superposición lee la pantalla y el registro del juego para resolver el tablero.

  • The game's rules: all 31 Torture Instruments, the 17 Prison Incidents, the Objectives, the run themes (Tyranny, Opulence, Iron Law, Cage Fight), Rat Nests, Tusk and Prey marks, Scratch Marks.
  • The solver: a determinized Monte Carlo search (what's hidden behind doors is drawn again for every playout: no peeking): the playouts' moves by a small policy network trained on the search's own choices, a small value network at their horizon.
Aprendizaje automáticoC#MITGitHub

coralnpu

google-coral

2,687estrellas+2in 24h
coralnpu preview

A machine learning accelerator core designed for energy-efficient AI at the edge.

  • RV32IMF_Zve32x RISC-V instruction set (specifically rv32imf_zve32x_zicsr_zifencei_zbb)
  • 32-bit address space for applications and operating system kernels
Aprendizaje automáticoEmacs LispApache-2.0GitHub

Objectron

google-research-datasets

2,362estrellas+2in 24h
Objectron preview

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and planes. In each video, the camera moves around and above the object and captures it from different views. Each object is annotated with a 3D bounding box. The 3D bounding box describes the object’s position, orientation, and dimensions. The dataset contains about 15K annotated video clips and 4M annotated images in the following categories: bikes, books, bottles, cameras, cereal boxes, chairs, cups, laptops, and shoes

  • 15000 annotated videos and 4M annotated images
  • All samples include high-res images, object pose, camera pose, point-cloud, and surface planes.
Aprendizaje automáticoJupyter NotebookGitHub

gin-config

google

2,159estrellas+2in 24h

Gin provides a lightweight configuration framework for Python

  • Automatic logging of all configured parameter values (the "operative config"), including TensorBoard integration.
  • "Macros", to specify a value used in multiple places within a config, as well as Python-defined constants.
Aprendizaje automáticoPythonApache-2.0GitHub

NextTransformer

Interactive-Active-AI

407estrellas+2in 24h
NextTransformer preview

:sunrise: Un marco de código abierto, completo y de vanguardia para los Transformers de nueva generación, con evaluaciones comparativas que igualan el cómputo y una plataforma para la investigación autónoma de arquitecturas.

Aprendizaje automáticoPythonMITGitHub