Skip to content
Catégories de projets

Apprentissage automatique · GitHub

Explorez les outils pour entraîner, évaluer et exécuter des modèles, et comparez leur popularité.

Projets GitHub utiles

4,743 projets

CleverCSV

alan-turing-institute

1,344étoiles+1in 24h

CleverCSV is a Python package for handling messy CSV files. It provides a drop-in replacement for the builtin CSV module with improved dialect detection, and comes with a handy command line application for working with CSV files.

Apprentissage automatiquePythonMITGitHub

Texo

alephpi

920étoiles+1in 24h
Texo preview

A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识别模型，仅20M参数量，可在浏览器中运行。训练全流程代码开源，以便自学复现。

  • Free and open-source.
  • Fast and lightweight inference.
Apprentissage automatiquePythonAGPL-3.0GitHub

End-to-end-ASR-Pytorch

Alexander-H-Liu

1,209étoiles+1in 24h
End-to-end-ASR-Pytorch preview

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

  • On-the-fly feature extraction using torchaudio as backend
  • Character/subword2/word encoding of text
Apprentissage automatiquePythonMITGitHub

MNISTVision

aliasgharebrahimi

93étoiles+1in 24h
MNISTVision preview

An optimized handwritten digit recognition model delivering exceptional accuracy, high-speed performance, and compatibility with low-end hardware, supported by comprehensive documentation, experiment tracking, data-driven decision-making, effective troubleshooting, and a modular project structure.

  • Maximum execution speed
  • Highly robust optimization
Apprentissage automatiquePythonApache-2.0GitHub

vs-mlrt

AmusementClub

493étoiles+1in 24h

Efficient CPU/GPU ML Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2/v3, Real-CUGAN, RIFE, SCUNet, ArtCNN and more!)

Apprentissage automatiqueC++GPL-3.0GitHub

Deep-Learning-Interview-Book

amusi

8,962étoiles+1in 24h
Deep-Learning-Interview-Book preview

Guide d'entretiens en apprentissage profond couvrant les mathématiques, l'apprentissage automatique, l'apprentissage profond, la vision par ordinateur, le traitement du langage naturel, SLAM et d'autres domaines.

Apprentissage automatiqueGitHub

mlx-tune

ARahim3

1,470étoiles+1in 24h

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.

Apprentissage automatiquePythonApache-2.0GitHub

light-ocr

arcships

661étoiles+1in 24h
light-ocr preview

Fast, offline OCR for Node.js & C++. PP-OCRv6 with Core ML / WebGPU hardware acceleration — recognize text in images with confidence scores & coordinates. npm: @arcships/light-ocr

Apprentissage automatiqueC++Apache-2.0GitHub

ROMP

Arthur151

1,545étoiles+1in 24h
ROMP preview

Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]

Apprentissage automatiquePythonApache-2.0GitHub

fast-volleyball-tracking-inference

asigatchov

76étoiles+1in 24h
fast-volleyball-tracking-inference preview

Fast Volleyball Tracking Inference: Real-time volleyball ball detection and tracking at 100 FPS on CPU (Intel i5-10400F). Powered by an optimized ONNX model, outputs ball coordinates to CSV, with optional video visualization. Ideal for sports analytics and computer vision research.

Apprentissage automatiquePythonGitHub