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

4,629 プロジェクト

ANE

maderix

7,301スター

リバースエンジニアリングで解析した非公開 API を使い、Apple Neural Engine 上でニューラルネットワークを学習

機械学習Objective-CMITGitHub

NNPACK

Maratyszcza

1,710スター

Acceleration package for neural networks on multi-core CPUs

  • Fast convolution based on Fourier transform (for kernels up to 16x16 without stride)
  • Fast convolution based on Winograd transform (for 3x3 kernels without stride)
機械学習CBSD-2-ClauseGitHub

lime

marcotcr

12,169スター
lime preview

Lime: Explaining the predictions of any machine learning classifier

機械学習JavaScriptBSD-2-ClauseGitHub

BinaryNet

MatthieuCourbariaux

1,068スター

Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

機械学習PythonBSD-3-ClauseGitHub

YOLOv6

meituan

5,892スター
YOLOv6 preview

YOLOv6: a single-stage object detection framework dedicated to industrial applications.

機械学習Jupyter NotebookGPL-3.0GitHub

shimmy

Michael-A-Kuykendall

6,014スター

⚡ Rust のみで実装された WebGPU 推論エンジン。OpenAI API 互換で、GGUF をネイティブにサポートし、あらゆる GPU で動作します。Python も llama.cpp も不要。単一バイナリで動作します。

  • ⚡ TurboShimmy INT4 KV Cache — About 7× lower KV-cache memory in tested configurations. Run Llama-3.2-3B on 4 GB GPUs.
  • 🚀 OpenAI SDK Compatibility — Chat completions, text completions, streaming, and model endpoints. Works with OpenAI SDKs and tools using that surface.
機械学習RustApache-2.0GitHub

boxmot

mikel-brostrom

8,325スター
boxmot preview

BoxMOT: Pluggable Python and C++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

機械学習PythonAGPL-3.0GitHub

TDC

mims-harvard

1,300スター
TDC preview

Therapeutics Commons (TDC): Multimodal Foundation for Therapeutic Science

  • Diverse areas of therapeutics development: TDC covers a wide range of learning tasks, including target discovery, activity screening, efficacy, safety, and manufacturing across biomedical products, including small molecules, antibodies, and vaccines.
  • Ready-to-use datasets: TDC is minimally dependent on external packages. Any TDC dataset can be retrieved using only three lines of code.
機械学習Jupyter NotebookMITGitHub

best-of-jupyter

ml-tooling

1,248スター
best-of-jupyter preview

🏆 A ranked list of awesome Jupyter Notebook, Hub and Lab projects (extensions, kernels, tools). Updated weekly.

3,306スター
mljar-supervised preview

Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation

601スター
BertWithPretrained preview

An implementation of the BERT model and its related downstream tasks based on the PyTorch framework. @跟我学机器学习

4,708スター

潜在空間を探索し、テキストプロンプト間をモーフィングして、Stable Diffusion で 🔥 動画を作成

機械学習PythonApache-2.0GitHub