Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
- ocr
- chineseocr
- pdf2markdown
- pp-ocr
47,133 repositories indexed
1–24 of 43 · Most stars
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
🦉 Data Versioning and ML Experiments
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
COLMAP - Structure-from-Motion and Multi-View Stereo
NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
Refine high-quality datasets and visual AI models
Fast and Accurate ML in 3 Lines of Code
Build, Manage and Deploy AI/ML Systems
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
Infrastructure for continually self‑improving agents
Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.
Visual localization made easy with hloc
Artificial Intelligence Infrastructure-as-Code Generator.
3D Computer Vision Framework
Trainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2
Accelerated deep learning R&D
Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works with PyTorch and TensorFlow.
A large collection of system log datasets for AI-driven log analytics [ISSRE'23]
HyperLogLog with lots of sugar (Sparse, LogLog-Beta bias correction and TailCut space reduction) brought to you by Axiom
🏅State-of-the-art learned data structure that enables fast lookup, predecessor, range searches and updates in arrays of billions of items using orders of magnitude less space than traditional indexes
Tasks Assessing Protein Embeddings (TAPE), a set of five biologically relevant semi-supervised learning tasks spread across different domains of protein biology.
Little Ball of Fur - A graph sampling extension library for NetworKit and NetworkX (CIKM 2020)
TranslatedHuashu (花叔, "Uncle Hua") open-sourced global bird sticker library · Stickers for all 11,064 living bird species, with names in 43 languages and structured data
A Euclidean diffusion model for structure-based drug design.