ByteTrack
FoundationVision
6,808étoiles+2in 24h
[ECCV 2022] ByteTrack: Multi-Object Tracking by Associating Every Detection Box
Apprentissage automatique · GitHub
Explorez les outils pour entraîner, évaluer et exécuter des modèles, et comparez leur popularité.
Projets GitHub utiles
4,743 projets
ML2021-Spring
ga642381
1,049étoiles+2in 24h
**Official** 李宏毅 (Hung-yi Lee) 機器學習 Machine Learning 2021 Spring
img2img-turbo
GaParmar
2,495étoiles+2in 24h
One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more
text-classification-cnn-rnn
gaussic
4,303étoiles+2in 24h
CNN-RNN中文文本分类，基于TensorFlow
machine-learning-visualized
gavinkhung
2,101étoiles+2in 24h
Algorithmes d’apprentissage automatique implémentés et dérivés à partir des premiers principes avec Jupyter Notebooks et NumPy.
DiffDock
gcorso
1,607étoiles+2in 24h
Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
FastMOT
GeekAlexis
1,220étoiles+2in 24h
High-performance multiple object tracking based on YOLO, Deep SORT, and KLT 🚀
Girls-In-AI
girls-in-ai
3,426étoiles+2in 24h
免费学代码系列：小白python入门、数据分析data analyst、机器学习machine learning、深度学习deep learning、kaggle实战
TartarusSolver
glcoder
57étoiles+2in 24h
Fournit des indications de déplacement pour Tartarus Prison dans Torchlight: Infinite. Une superposition lit l’écran et le journal du jeu pour résoudre le plateau.
- The game's rules: all 31 Torture Instruments, the 17 Prison Incidents, the Objectives, the run themes (Tyranny, Opulence, Iron Law, Cage Fight), Rat Nests, Tusk and Prey marks, Scratch Marks.
- The solver: a determinized Monte Carlo search (what's hidden behind doors is drawn again for every playout: no peeking): the playouts' moves by a small policy network trained on the search's own choices, a small value network at their horizon.
coralnpu
google-coral
2,687étoiles+2in 24h
A machine learning accelerator core designed for energy-efficient AI at the edge.
- RV32IMF_Zve32x RISC-V instruction set (specifically rv32imf_zve32x_zicsr_zifencei_zbb)
- 32-bit address space for applications and operating system kernels
tapnet
google-deepmind
2,260étoiles+2in 24h
Tracking Any Point (TAP)
gin-config
2,159étoiles+2in 24h
Gin provides a lightweight configuration framework for Python
- Automatic logging of all configured parameter values (the "operative config"), including TensorBoard integration.
- "Macros", to specify a value used in multiple places within a config, as well as Python-defined constants.
sentencepiece
12,170étoiles+2in 24h
Unsupervised text tokenizer for Neural Network-based text generation.
tf-quant-finance
5,568étoiles+2in 24h
High-performance TensorFlow library for quantitative finance.
weightslab
GrayboxTech
179étoiles+2in 24h
Monitoring platform for ML teams building real‑world AI at scale.
PlotNeuralNet
HarisIqbal88
25,089étoiles+2in 24h
Code LaTeX pour créer des schémas de réseaux neuronaux
mind-ar-js
hiukim
2,761étoiles+2in 24h
Web Augmented Reality. Image Tracking, Face Tracking. Tensorflow.js
course
huggingface
4,358étoiles+2in 24h
The Hugging Face course on Transformers
huggingface.js
huggingface
2,608étoiles+2in 24h
Use Hugging Face with JavaScript
NextTransformer
Interactive-Active-AI
407étoiles+2in 24h
:sunrise: Un framework open source complet et de pointe pour les Transformers de nouvelle génération, avec des évaluations comparatives à budget de calcul égal et une plateforme de recherche autonome sur les architectures.
CompressAI
InterDigitalInc
1,659étoiles+2in 24h
A PyTorch library and evaluation platform for end-to-end compression research
FirstLight-Zero
Jaasssoooonnnnn
18étoiles+2in 24h
AlphaZero-style self-play Clash Royale. It beats a human-data imitation model
PythonPark
Jack-Cherish
11,923étoiles+2in 24h
Python 开源项目之「自学编程之路」，保姆级教程：AI实验室、宝藏视频、数据结构、学习指南、机器学习实战、深度学习实战、网络爬虫、大厂面经、程序人生、资源分享。
awesome-self-supervised-learning
jason718
6,448étoiles+2in 24h
Une liste sélectionnée d'excellentes méthodes d'apprentissage auto-supervisé