Starred repositories
QuatRE: Relation-Aware Quaternions for Knowledge Graph Embeddings (TheWebConf WWW 2022) (Pytorch)
A PyTorch implementation of the Relational Graph Convolutional Network (RGCN).
Source code for EvalNE, a Python library for evaluating Network Embedding methods.
SimplE Embedding for Link Prediction in Knowledge Graphs
Graph Embedding Evaluation / Code and Datasets for "Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations" (Bioinformatics 2020)
Representation learning for link prediction within social networks
CogDL: A Comprehensive Library for Graph Deep Learning (WWW 2023)
The official PyTorch implementation of "Pathfinder Discovery Networks for Neural Message Passing" (WebConf '21)
A curated list of data mining papers about fraud detection.
StellarGraph - Machine Learning on Graphs
Load an image file into a numpy array with Exif orientation support. Prevents upside-down and sideways images!
The world's simplest facial recognition api for Python and the command line
🚪✊Knock Knock: Get notified when your training ends with only two additional lines of code
Experimental Gradient Boosting Machines in Python with numba.
Tesseract Open Source OCR Engine (main repository)
scikit-learn: machine learning in Python
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Tez is a super-simple and lightweight Trainer for PyTorch. It also comes with many utils that you can use to tackle over 90% of deep learning projects in PyTorch.
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
Approaching (Almost) Any Machine Learning Problem
A toolkit for orchestrating distributed systems at any scale. It includes primitives for node discovery, raft-based consensus, task scheduling and more.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
An Open Source Machine Learning Framework for Everyone