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

io

tensorflow

739スター

Dataset, streaming, and file system extensions maintained by TensorFlow SIG-IO

機械学習C++Apache-2.0GitHub
1,584スター

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

機械学習PythonApache-2.0GitHub

privacy

tensorflow

2,038スター

Library for training machine learning models with privacy for training data

機械学習PythonApache-2.0GitHub

recommenders

tensorflow

2,040スター

TensorFlow Recommenders is a library for building recommender system models using TensorFlow.

機械学習PythonApache-2.0GitHub
635スター
recommenders-addons preview

Additional utils and helpers to extend TensorFlow when build recommendation systems, contributed and maintained by SIG Recommenders.

  • Make key-value data structure (dynamic embedding) trainable in TensorFlow
  • Get better recommendation effect compared to static embedding mechanism with no hash conflicts
機械学習CudaApache-2.0GitHub

serving

tensorflow

6,363スター

柔軟で高性能な機械学習モデルのサービングシステム

機械学習C++Apache-2.0GitHub

tcav

tensorflow

653スター

Code for the TCAV ML interpretability project

機械学習Jupyter NotebookApache-2.0GitHub

tfx

tensorflow

2,190スター
tfx preview

TFX is an end-to-end platform for deploying production ML pipelines

機械学習PythonApache-2.0GitHub

tensorforce

tensorforce

3,302スター

Tensorforce: a TensorFlow library for applied reinforcement learning

  • Network layers: Fully-connected, 1- and 2-dimensional convolutions, embeddings, pooling, RNNs, dropout, normalization, and more; plus support of Keras layers.
  • Network architecture: Support for multi-state inputs and layer (block) reuse, simple definition of directed acyclic graph structures via register/retrieve layer, plus support for arbitrary architectures.
機械学習PythonApache-2.0GitHub

TPA

tensorgi

465スター

[NeurIPS 2025 Spotlight] TPA: Tensor ProducT ATTenTion Transformer (https://arxiv.org/abs/2501.06425)

HyperPose

tensorlayer

1,261スター
HyperPose preview

Library for Fast and Flexible Human Pose Estimation

  • Customise training, evaluation, visualisation, pre-processing and post-processing in pose estimation.
  • Customise model architectures (e.g., OpenPose, Pifpaf, PoseProposal Network) and training datasets.