pbdl-book
tum-pbs
1,378stars+2in 24h
Welcome to the Physics-based Deep Learning Book v0.3 - the GenAI Edition
Machine Learning · GitHub
Train, evaluate, and run machine learning models.
Useful GitHub projects
4,743 projects
darts
unit8co
9,585stars+2in 24h
A python library for user-friendly forecasting and anomaly detection on time series.
- Forecasting Models: A large collection of forecasting models for regression as well as classification tasks; from statistical models (such as ARIMA) to deep learning models (such as N-BEATS). See the forecasting models below.
- Multivariate Support: TimeSeries can be multivariate - i.e., contain multiple time-varying dimensions/columns instead of a single scalar value. Many models can consume and produce multivariate series.
Book3_Elements-of-Mathematics
Visualize-ML
7,709stars+2in 24h
Book_3_《数学要素》 | 鸢尾花书：从加减乘除到机器学习；上架；欢迎继续纠错，纠错多的同学还会有赠书！
Book5_Essentials-of-Probability-and-Statistics
Visualize-ML
3,826stars+2in 24h
Book_5_《统计至简》 | 鸢尾花书：从加减乘除到机器学习；上架！
Book7_Visualizations-for-Machine-Learning
Visualize-ML
3,422stars+2in 24h
Book_7_《机器学习》 | 鸢尾花书：从加减乘除到机器学习；欢迎批评指正
3,646stars+2in 24h
“Math Isn’t Hard”: *Linear Algebra Made Easy*, Volumes 1 and 2, covering 66 topics. Feedback and corrections are welcome.
sdnext
vladmandic
7,378stars+2in 24h
SD.Next: All-in-one WebUI for AI generative image and video creation, captioning and processing
- Generate and edit: Create images or videos from text or images; edit, inpaint, outpaint, refine, detail
- Guide generation: Use LoRA, ControlNet, IP-Adapters, and Prompt enhancement
webdataset
webdataset
3,219stars+2in 24h
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
Xsdsh-purge
xiaoshe1337-star
166stars+2in 24h
沿用了此项目：https://github.com/YuJunZhiXue/dsh-purge 专注于deepseek harness破甲|逆向|渗透| 适配最新版deepseek harness ：deepseek v4.1 flash 最新版 更新q群562341656
projectlearn-project-based-learning
Xtremilicious
6,400stars+2in 24h
A curated list of project tutorials for project-based learning.
DIS
xuebinqin
2,591stars+2in 24h
This is the repo for our new project Highly Accurate Dichotomous Image Segmentation
ml-road
yanshengjia
4,982stars+2in 24h
Machine Learning and Agentic AI Resources, Practice and Research
video-subtitle-extractor
YaoFANGUK
9,724stars+2in 24h
A GUI tool and deep-learning framework for extracting hard-coded subtitles from videos and generating SRT files. It requires no third-party API and performs text recognition locally. It includes subtitle-region detection and subtitle-content extraction.
OpenMLDB
4paradigm
1,718stars+1in 24h
OpenMLDB is an open-source machine learning database that provides a feature platform computing consistent features for training and inference.
pytorch-nested-unet
4uiiurz1
1,056stars+1in 24h
PyTorch implementation of UNet++ (Nested U-Net).
approachingalmost
abhishekkrthakur
8,409stars+1in 24h
Approaching (Almost) Any Machine Learning Problem
mace
ACEsuit
1,412stars+1in 24h
MACE - Fast and accurate machine learning interatomic potentials with higher order equivariant message passing.
adapters
adapter-hub
2,833stars+1in 24h
A Unified Library for Parameter-Efficient and Modular Transfer Learning
Machine-Learning-Links-And-Lessons-Learned
adeshpande3
1,007stars+1in 24h
List of all the lessons learned, best practices, and links from my time studying machine learning
- It's also model dependent. Normalization will likely help for linear models like linear/logistic reg, but won't be as helpful for deep learning models and neural networks.
- In order to determine whether it will help or not, visualize your data to see what type of features you're dealing with. Do you have some features that have values around 1000 or 2000? Do you have some that are only 0.1 or 0.2? If so, normalizing those inputs is likely a good idea.
multi-object-tracker
adipandas
698stars+1in 24h
Multi-object trackers in Python
underPINN
Aeroscience-Computations-Analysis-Lab
39stars+1in 24h
A modular, JAX-based framework for Physics-Informed Neural Networks, designed for scalable PDE-constrained learning with support for domain decomposition, attention mechanisms, and performance-oriented training.
face_recognition
ageitgey
56,893stars+1in 24h
The world's simplest facial recognition api for Python and the command line
- Identify specific facial features in a photograph
- Apply (horribly ugly) digital make-up
Plant-Disease-Classification
AhmadJeddi
49stars+1in 24h
A ResNet50-DCBAM deep learning framework for plant disease classification using the PlantVillage dataset with reproducible training and evaluation pipelines.
- ResNet50 backbone with pretrained ImageNet weights
- Channel attention
From-0-to-Research-Scientist-resources-guide
ahmedbahaaeldin
7,693stars+1in 24h
Detailed and tailored guide for undergraduate students or anybody want to dig deep into the field of AI with solid foundation.