基于NPS 0.26.10 版本二开而来，NPS接力项目。公益云NPS：https://natnps.com

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

Production First and Production Ready End-to-End Speech Recognition Toolkit

Robust Speech Recognition via Large-Scale Weak Supervision

Main gperftools repository

A Survey and Benchmark for Automatic Surface Reconstruction from Point Clouds

[ICPR 2022] Data, code and pretrained models for Deep Surface Reconstruction from Point Clouds with Visibility Information

implementation of local outlier factor on pcl

Accurate, Detailed, and Automatic Modelling of Laser-Scanned Trees

C++ implementation of the Python Numpy library

open-source 3D scanning and processing pipeline

COLMAP - Structure-from-Motion and Multi-View Stereo

Google Brain AutoML

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

This is an official implementation of our CVPR 2020 paper "HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation" (https://arxiv.org/abs/1908.10357)

Torchreid: Deep learning person re-identification in PyTorch.

Open Source TOF Lidar

Multi-person Human Pose Estimation with HRNet in Pytorch

A simple baseline for one-shot multi-object tracking

AI Roadmap:机器学习(Machine Learning)、深度学习(Deep Learning)、对抗神经网络(GAN），图神经网络（GNN），NLP，大数据相关的发展路书(roadmap), 并附海量源码（python，pytorch）带大家消化基本知识点，突破面试，完成从新手到合格工程师的跨越，其中深度学习相关论文附有tensorflow caffe官方源码，应用部分含推荐算法…

CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark (CVPR2019)

Code for the paper "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.

[ECCV2020] a toolbox of light-reid learning for faster inference, speed both feature extraction and retrieval stages up to >30x

🍊 📊 💡 Orange: Interactive data analysis

Robust realtime face and facial landmark tracking on CPU with Unity integration

The world's simplest facial recognition api for Python and the command line

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

超轻量级中文ocr，支持竖排文字识别, 支持ncnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M