Skip to content
项目分类

机器学习 · GitHub

发现模型训练、评估与推理框架,比较深度学习和机器学习项目的社区关注度。

实用 GitHub 项目

12,806 个项目
551星标
Rectlabel-support preview

RectLabel is an offline image annotation tool for object detection and segmentation.

  • Using text and box prompts of Segment Anything Model 3, multiple objects are labeled at once
  • Label polygons and pixels using Segment Anything Model 2
机器学习Jupyter NotebookGitHub
130星标
dreamforge preview

Turn world-model imagination into corrective training data for robot policies — a single-GPU, falsifiable pipeline (SmolVLA · LIBERO · CEM · paired simulator replays).

1,557星标

Machine learning powered Karaoke app (with scores!)

  • Bring your library — scan local audio, video, and UltraStar files, or connect Plex, Jellyfin, or Navidrome. Existing provider and folder playlists appear as read-only navigation.
  • Prepare tracks locally — separate vocals with UVR Karaoke or Demucs, then use LRCLIB, local or pasted LRC, or automatic transcription and alignment for lyrics.
机器学习TypeScriptGPL-3.0GitHub
1,791星标
ESP32-CAM_MJPEG2SD preview

ESP32 Camera motion capture application to record JPEGs to SD card as AVI files and stream to browser as MJPEG. If a microphone is installed then a WAV file is also created. Files can be uploaded via FTP or downloaded to browser.

56星标
Lithicsoft-Trainer-Forge preview

Professional Trainer Studio Generator Suite 2026 – Open Source AI Coaching Toolkit

  • Gradient Perturbation Engine - Applies controlled noise to backpropagation paths - Prevents weight-exfiltration via side-channel analysis
  • Behavioral Polymorphism - Generates multiple functionally-equivalent inference paths - Makes runtime profiling unreliable

deepshot

saccofrancesco

175星标

AI-powered NBA game outcome predictor that uses advanced team stats and trend-based features to forecast winners and track model performance

  • Data-Driven Predictions – Powered by real NBA stats from Basketball Reference.
  • Real-Time Interface – Visualize upcoming matchups and model predictions with a sleek NiceGUI web frontend.
机器学习Jupyter NotebookMITGitHub

EdgeNets

sacmehta

414星标

This repository contains the source code of our work on designing efficient CNNs for computer vision

ESPNetv2

sacmehta

456星标

A light-weight, power efficient, and general purpose convolutional neural network

RIDNet

saeed-anwar

369星标
RIDNet preview

Pytorch code for "Real image denoising with feature attention", ICCV (Oral), 2019.

544星标
Microservices-Based-Algorithmic-Trading-System preview

MBATS is a docker based platform for developing, testing and deploying Algorthmic Trading strategies with a focus on Machine Learning based algorithms.

  • Infrastructure as Code – less than 5 minutes from scratch to a fully functional trading infrastructure.
  • Backtesting and Live trading Forex using Oanda Broker API (Can be easily be modified to accommodate IB for Equity).
机器学习PythonBSD-3-ClauseGitHub