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

12,803 プロジェクト

v2x-vit

DerrickXuNu

348スター

[ECCV2022] Official Implementation of paper "V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer"

strwythura

DerwenAI

233スター

Strwythura: construct an entity-resolved knowledge graph from structured data sources and unstructured content sources, implementing an ontology pipeline, plus context engineering for optimizing AI application outcomes within a specific domain. This produces a Streamlit app, with MLOps instrumentation.

atlas

dessa-oss

292スター
atlas preview

An Open Source, Self-Hosted Platform For Applied Deep Learning Development

  • Self-hosted: run Atlas on a single node e.g. your latop, or multi-node cluster e.g. on-premise servers or cloud clusters (AWS/GCP/etc.)
  • Job scheduling: Collaborate with your team by scheduling and running concurrent ML jobs remotely on your cluster & fully utilize your system resources.
機械学習PythonApache-2.0GitHub

FPN_Tensorflow

DetectionTeamUCAS

352スター

This is a tensorflow re-implementation of Feature Pyramid Networks for Object Detection.

機械学習Jupyter NotebookMITGitHub
240スター

This is a tensorflow implementation of R2CNN++: Multi-Dimensional Attention Based Rotation Invariant Detector with Robust Anchor Strategy.

determined

determined-ai

3,246スター
determined preview

Determinedは、分散学習、ハイパーパラメータ調整、実験の追跡、リソース管理を簡素化するオープンソースの機械学習プラットフォームです。PyTorchとTensorFlowに対応しています。

Cross-Lingual-Voice-Cloning

deterministic-algorithms-lab

359スター

Tacotron 2 - PyTorch implementation with faster-than-realtime inference modified to enable cross lingual voice cloning.

機械学習Jupyter NotebookBSD-3-ClauseGitHub

tevr-asr-tool

DeutscheKI

410スター

State-of-the-art (ranked #1 Aug 2022) German Speech Recognition in 284 lines of C++. This is a 100% private 100% offline 100% free CLI tool.

224スター

PackInspect is a low-code visual inspection tool built using TensorFlow and Streamlit. It allows users to detect defects in bottle images (or similar packaging components) by uploading images or capturing them via webcam.