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

4,624 projets

PyCharm-PixelLens

srwi

102étoiles
PyCharm-PixelLens preview

Free PyCharm image viewer plugin for visualizing and debugging NumPy, OpenCV, PyTorch, TensorFlow, JAX, and PIL data.

  • View NumPy, OpenCV, PyTorch, TensorFlow, JAX and Pillow (PIL) data as image
  • View entire batches (fourth dimension) or individual channels of the data
Apprentissage automatiqueKotlinGPL-3.0GitHub

puffer

StanfordSNR

922étoiles

Puffer is a free live TV streaming website and a research study at Stanford using machine learning to improve video streaming

Apprentissage automatiqueC++GitHub

log-generator

summved

58étoiles

This tool will be invaluable for: SIEM Testing - Generate realistic multi-source logs Security Training - Reproducible scenarios for education Development - Consistent test data for log processing systems Research - Controlled log generation for cybersecurity studies

  • 12 log sources — endpoint, application, server, firewall, cloud, authentication, database, webserver, email, backup, microservices, and IoT. Each carries a source host and component, and rates are driven entirely by config.
  • MITRE ATT&CK tagging and filtering — logs are auto-mapped to techniques/tactics; generate only matching logs with --mitre-technique / --mitre-tactic. List and analyze coverage with mitre-list and mitre-coverage.
Apprentissage automatiqueTypeScriptGitHub

rockpool

synsense

92étoiles
rockpool preview

A machine learning library for spiking neural networks. Supports training with both torch and jax pipelines, and deployment to neuromorphic hardware.

Apprentissage automatiquePythonAGPL-3.0GitHub

TeaLeaves

taylorsatula

46étoiles
TeaLeaves preview

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking curves, compare variants with evidence — not vibes.

Apprentissage automatiquePythonGitHub

TeleFuser

Tele-AI

36étoiles

High-performance runtime for real-time multimodal generation and world models—streaming inference, stateful sessions, and distributed GPU execution.

  • one-shot image generation
  • offline video generation
Apprentissage automatiquePythonApache-2.0GitHub

DigitSuo

tetsuo-ai

48étoiles
DigitSuo preview

handwritten digit recognition system using a custom neural network architecture. Built with C, it features both training capabilities and an interactive recognition interface. >98% accuracy on the MNIST dataset.

Apprentissage automatiqueCMITGitHub

tevatron

texttron

753étoiles

Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.

  • Training billion-scale LLM neural retriever on GPUs and TPUs.
  • Parameter efficient tuning with LoRA.
Apprentissage automatiquePythonApache-2.0GitHub

sslsv

theolepage

41étoiles
sslsv preview

Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker Verification (SV).

  • Supervised and Self-supervised datasets (siamese and DINO sampling)
  • Audio augmentation (noise and reverberation)
Apprentissage automatiquePythonMITGitHub

fire-detection-cnn

tobybreckon

571étoiles
fire-detection-cnn preview

real-time fire detection in video imagery using a convolutional neural network (deep learning) - from our ICIP 2018 paper (Dunnings / Breckon) + ICMLA 2019 paper (Samarth / Bhowmik / Breckon)

Apprentissage automatiquePythonMITGitHub

tsl

TorchSpatiotemporal

392étoiles

tsl: a PyTorch library for processing spatiotemporal data.

  • Create Custom Models and Datasets Easily build your own custom models and datasets for spatiotemporal data analysis. Whether you're working with sensor networks, environmental data, or any other spatiotemporal domain, tsl's high-level APIs empower you to develop tailored solutions.
  • Access a Wealth of Existing Datasets and Models Leverage a vast collection of datasets and models from the spatiotemporal data processing literature. Explore and benchmark against state-of-the-art baselines, and test your brand new model on widely used public datasets.
Apprentissage automatiquePythonMITGitHub

tmrl

trackmania-rl

750étoiles
tmrl preview

Reinforcement Learning for real-time applications

  • Analog control from screenshots: The tmrl example pipeline trains policies that are able to drive from raw screenshots captured in real-time. For beginners, we also provide simpler rangefinder ("LIDAR") observations, which are less potent but easier to learn from. The example pipeline controls the game via a virtual gamepad, which enables analog actions.
  • Models: To process LIDAR measurements, the example tmrl pipeline uses a Multi-Layer Perceptron (MLP). To process raw camera images (snapshots), it uses a Convolutional Neural Network (CNN). These models learn the physics of the game from histories or observations equally spaced in time.
Apprentissage automatiquePythonMITGitHub