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

12,805 プロジェクト

dance

OmicsML

390スター

DANCE: a deep learning library and benchmark platform for single-cell analysis

機械学習PythonBSD-2-ClauseGitHub

PyMO

omimo

367スター

A library for machine learning research on motion capture data

pyresparser

OmkarPathak

958スター
pyresparser preview

A simple resume parser used for extracting information from resumes

  • Extract mobile numbers
  • Extract total experience
機械学習PythonGPL-3.0GitHub
999スター
open-metric-learning preview

Metric learning and retrieval pipelines, models and zoo.

  • Logginglogger = TensorBoardPipelineLogger() logger = NeptunePipelineLogger() logger = WandBPipelineLogger() logger = MLFlowPipelineLogger() logger = ClearMLPipelineLogger() - PMLfrom pytorch_metric_learning import losses criterion = losses.TripletMarginLoss(0.2, "all") pred = ViTExtractor()(data) criterion(pred, gts)
機械学習PythonApache-2.0GitHub
506スター

One-paper-one-short-contribution-summary of all latest image/burst/video Denoising papers with code & citation published in top conference and journal.

models

onnx

9,859スター
models preview

A collection of pre-trained, state-of-the-art models in the ONNX format

機械学習Jupyter NotebookApache-2.0GitHub

onnxsim

onnxsim

4,420スター
onnxsim preview

Simplify your onnx model

  • Shape inference. Propagates tensor shapes through the graph — including partial shape evaluation via ONNX data propagation — to unlock more folding.
  • Correctness checking. Optionally validates the simplified model against the original on N random inputs (the positional check_n argument, with configurable --check-rtol/--check-atol). Choose how the generated inputs are filled with --input-fill (Python: input_fill=): random (uniform [0, 1), the default), ones, zeros or arange.
機械学習PythonApache-2.0GitHub

dlstreamer

open-edge-platform

648スター
dlstreamer preview

Deep Learning Streamer (DL Streamer) Pipeline Framework is an open-source streaming media analytics framework, based on GStreamer* multimedia framework, for creating complex media analytics pipelines for the Cloud or at the Edge.

mmaction2

open-mmlab

5,201スター
mmaction2 preview

OpenMMLabの次世代ビデオ理解ツールボックスおよびベンチマーク

  • Modular design: We decompose a video understanding framework into different components. One can easily construct a customized video understanding framework by combining different modules.
  • Support five major video understanding tasks: MMAction2 implements various algorithms for multiple video understanding tasks, including action recognition, action localization, spatio-temporal action detection, skeleton-based action detection and video retrieval.
機械学習PythonApache-2.0GitHub

mmagic

open-mmlab

7,482スター
mmagic preview

OpenMMLab のマルチモーダルな高度生成・知的創作ツールボックス。魔法を解き放つ 🪄:生成 AI(AIGC)、使いやすい API、優れたモデルズー、拡散モデルを備え、テキストからの画像生成や、画像・動画の復元と画質向上などに対応します。

  • State of the Art Models MMagic provides state-of-the-art generative models to process, edit and synthesize images and videos.
機械学習Jupyter NotebookApache-2.0GitHub

mmfashion

open-mmlab

1,377スター
mmfashion preview

Open-source toolbox for visual fashion analysis based on PyTorch

  • Flexible: modular design and easy to extend
  • Friendly: off-the-shelf models for layman users
機械学習PythonApache-2.0GitHub

mmpretrain

open-mmlab

3,863スター
mmpretrain preview

OpenMMLab Pre-training Toolbox and Benchmark

  • Various backbones and pretrained models
  • Rich training strategies (supervised learning, self-supervised learning, multi-modality learning etc.)
機械学習PythonApache-2.0GitHub

OpenUnReID

open-mmlab

411スター

PyTorch open-source toolbox for unsupervised or domain adaptive object re-ID.

機械学習PythonApache-2.0GitHub

ThoughtSource

OpenBioLink

1,018スター
ThoughtSource preview

A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/

機械学習Jupyter NotebookMITGitHub

awesome-RLHF

opendilab

4,439スター
awesome-RLHF preview

A curated list of reinforcement learning with human feedback resources (continually updated)

CleanS2S

opendilab

543スター

High-quality and streaming Speech-to-Speech interactive agent in a single file. 只用一个文件实现的流式全双工语音交互原型智能体!

機械学習PythonApache-2.0GitHub

TenSEAL

OpenMined

1,042スター

A library for doing homomorphic encryption operations on tensors

  • :key: Encryption/Decryption of vectors of integers using BFV
  • :old_key: Encryption/Decryption of vectors of real numbers using CKKS
機械学習C++Apache-2.0GitHub
4,756スター

Transformerモデル向けの高速推論エンジン

  • Fast and efficient execution on CPU and GPUThe execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many advanced optimizations: layer fusion, padding removal, batch reordering, in-place operations, caching mechanism, etc.
  • Quantization and reduced precisionThe model serialization and computation support weights with reduced precision: 16-bit floating points (FP16), 16-bit brain floating points (BF16), 16-bit integers (INT16), 8-bit integers (INT8) and AWQ quantization (INT4).

openpifpaf

openpifpaf

1,263スター
openpifpaf preview

Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.