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
450スター

Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera. This project prepares training and testing data for various deep learning projects such as 6D object pose estimation projects singleshotpose, as well as object detection and instance segmentation projects.

410スター
L3C-PyTorch preview

PyTorch Implementation of the CVPR'19 Paper "Practical Full Resolution Learned Lossless Image Compression"

機械学習PythonGPL-3.0GitHub
26スター
sentinel1-water-unet preview

Surface water from Sentinel-1 SAR with a U-Net (Wagner et al. 2024, Remote Sensing): PyTorch weights, SNAP preprocessing, Colab & JupyterLab notebooks

emonet

face-analysis

367スター

Official implementation of the paper "Estimation of continuous valence and arousal levels from faces in naturalistic conditions", Antoine Toisoul, Jean Kossaifi, Adrian Bulat, Georgios Tzimiropoulos and Maja Pantic, Nature Machine Intelligence, 2021

AITemplate

facebookincubator

4,732スター
AITemplate preview

AITemplateは、ニューラルネットワークを高性能なCUDA/HIP C++コードに変換するPythonフレームワークです。FP16 TensorCore(NVIDIA GPU)およびMatrixCore(AMD GPU)での推論に特化しています。

機械学習PythonApache-2.0GitHub

dynolog

facebookincubator

389スター

Dynolog is a telemetry daemon for performance monitoring and tracing. It exports metrics from different components in the system like the linux kernel, CPU, disks, Intel PT, GPUs etc. Dynolog also integrates with pytorch and can trigger traces for distributed training applications.

MCGrad

facebookincubator

53スター
MCGrad preview

MCGrad is a scalable and easy-to-use tool for multicalibration. It ensures your ML model predictions are well-calibrated not just globally (across all data), but also across virtually any segment defined by your features

機械学習Jupyter NotebookMITGitHub

nimble

facebookincubator

745スター

New and extensible file format for storage of large columnar datasets.

機械学習C++Apache-2.0GitHub

BenchMARL

facebookresearch

688スター
BenchMARL preview

BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.

  • A test CI with integration and training test routines that are run for all simulators and algorithms
  • Integration in the official TorchRL ecosystem for dedicated support

CodeGen

facebookresearch

778スター

Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.

dlrm

facebookresearch

4,076スター
dlrm preview

深層学習レコメンデーションモデル(DLRM)の実装

encodec

facebookresearch

4,073スター
encodec preview

最先端のディープラーニングに基づく音声コーデック。モノラル24 kHz音声とステレオ48 kHz音声の両方に対応します。

fairseq2

facebookresearch

1,153スター

FAIR Sequence Modeling Toolkit 2

  • First-party recipes for language model instruction finetuning and preference optimization
  • Multi-GPU, multi-node training using DDP, FSDP, and tensor parallelism. Supports 70B+ models.

flow_matching

facebookresearch

4,848スター
flow_matching preview

フローマッチングアルゴリズムを実装するためのPyTorchライブラリです。連続型と離散型のフローマッチング実装を備え、テキストと画像の両方のモダリティで実用的な例を提供します。

habitat-lab

facebookresearch

3,189スター
habitat-lab preview

さまざまなタスクや環境で具身AIエージェントを訓練するための、モジュール式の高水準ライブラリです。

HolisticTraceAnalysis

facebookresearch

567スター
HolisticTraceAnalysis preview

A library to analyze PyTorch traces.

  • Temporal Breakdown - Breakdown of time taken by the GPUs in terms of time spent in computation, communication, memory events, and idle time across all ranks.
  • Kernel Breakdown - Finds kernels with the longest duration on each rank.