Skip to content
プロジェクトカテゴリ

機械学習 · GitHub

モデルの学習・評価・推論に使うフレームワークを探し、注目度を比較できます。

便利なGitHubプロジェクト

12,809 プロジェクト

DiCE

interpretml

1,532スター

Generate Diverse Counterfactual Explanations for any machine learning model.

444スター

Interpret Community extends Interpret repository with additional interpretability techniques and utility functions to handle real-world datasets and workflows.

interpret-text

interpretml

431スター
interpret-text preview

A library that incorporates state-of-the-art explainers for text-based machine learning models and visualizes the result with a built-in dashboard.

51スター
open-jev-typed-decision-engine preview

Open reproduction of TypeSafe Jev: a 150M typed decision engine (noul/choice/score in one non-autoregressive pass, calibrated confidence). 0.697 vs Jev's 0.727, 2.5x better calibrated, 4x faster, free. Trains on a Colab T4 in 30 min.

機械学習PythonApache-2.0GitHub

book

introdeeplearning

256スター

Code for the book "Mathematical Introduction to Deep Learning: Methods, Implementations, and Theory"

DeepRFT

INVOKERer

274スター
DeepRFT preview

The code for 'Intriguing Findings of Frequency Selection for Image Deblurring' and 'Deep Residual Fourier Transformation for Single Image Deblurring'

gpu-jupyter

iot-salzburg

769スター
gpu-jupyter preview

GPU-Jupyter: Your GPU-accelerated JupyterLab with a rich data science toolstack, TensorFlow and PyTorch for your reproducible deep learning experiments.

機械学習Jupyter NotebookApache-2.0GitHub

kaira

ipc-lab

63スター
kaira preview

A PyTorch-based toolkit for simulating communication systems

  • Research-Oriented: Designed to accelerate communications research.
  • Versatility: Compatible with various data types and neural network architectures.

cookbook-2nd-code

ipython-books

742スター

Code of the IPython Cookbook, Second Edition, by Cyrille Rossant, Packt Publishing 2018 [read-only repository]

機械学習Jupyter NotebookMITGitHub

flsim

iQua

205スター

A simulation framework for Federated Learning written in PyTorch

機械学習PythonApache-2.0GitHub
26スター
2D-Motion-Interface preview

Plug-and-play 2D motion interface for real-world Motion Language Models

  • 🔌 Plug-and-play, at very low training cost. The interface is an external module: no modification and no fine-tuning of the pretrained MoLM. E_2D has 9.6M parameters (~22 h) and the real-video adapter A_real only 0.3M (~1 h), both on a single A100 40GB.
  • 📈 Comparable to 3D motion inputs. On HumanML3D motion captioning, Avg Drop vs 3D Input is −0.2% (TM2T), +0.4% (MotionGPT), and −2.8% (MG-MotionLLM).

grokfast

ironjr

585スター

Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"