DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Repository Index
47,133 repositories indexed
1–19 of 19 · Most stars
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
CVAT is a leading data annotation platform for image, video, audio, and 3D datasets. It offers open-source, cloud, and enterprise products, as well as labeling services, with AI-assisted labeling, quality assurance, team collaboration, analytics, and developer APIs.
- video-annotation
- computer-vision
- computer-vision-annotation
- image-annotation
pix2tex: Using a ViT to convert images of equations into LaTeX code.
The Triton Inference Server provides an optimized cloud and edge inferencing solution.
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
Blender addons to make the bridge between Blender and geographic data
- blender
- addon
- geospatial
- gis
《深入理解 AI Infra：量化分析与系统设计》（李博杰 著）开源书稿：从硬件约束和模型架构出发，量化推导 LLM 推理与训练系统设计。含全书正文、PDF、配套计算工具与实验
- accelerator
- ai-infra
- ai-infrastructure
- book
A Grammar of Graphics for Python
A Python package for interactive geospatial analysis and visualization with Google Earth Engine.
- google-earth-engine
- gis
- remote-sensing
- image-processing
Keep track of your inventory of 3D-printer filament spools.
- 3d-printing
- database
- inventory
- service
A python module for scientific analysis of 3D data based on VTK and Numpy
- 3d-graphics
- vtk
- 3d
- mesh
3D visualization of scientific data in Python
Super Fast and Accurate 3D Object Detection based on 3D LiDAR Point Clouds (The PyTorch implementation)
- 3d-object-detection
- lidar-point-cloud
- bevmap
- center
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.
- 3d-object-detection
- 3d-detection
- 3d-deep-learning
- pytorch
[IROS 2020] se(3)-TrackNet: Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic Domains
- robotics
- tracking
- computer-vision
- pose-estimation
A dataset of 2D imagery, 3D point cloud data, and 3D vehicle bounding box labels all generated using the Grand Theft Auto 5 game engine.
Gaussian processes and Bayesian optimization for images and hyperspectral data
- image-processing
- hyperspectral-images
- gaussian-processes
- bayesian-optimization
Accurate segmentation of bacterial microscope images using deep learning synthetically generated image data.
- microscopy
- image-processing
- segmentation
- biology