Contents Menu Expand Light mode Dark mode Auto light/dark mode
Kevin wiki 0.1 文档
Kevin wiki 0.1 文档

🚀 Tutorials

  • Jetson系列
    • Jetson DS Setup
    • 适用于Jetson和JetPack的PyTorch容器
    • NVIDIA Jetson上部署YOLOv8
    • Jetson Enable VNC server
  • LiDAR系列
    • SLAMTEC MAPPER应用笔记
    • Lidar-Camera Deep Fusion
    • R3LIVE RGB-colored, LiDAR-Inertial-Visual
  • Nvidia
    • NVIDIA DALI 图片预处理加速库
    • Automatic Augmentation pre-process
    • NVIDIA Omniverse
    • Omniverse Developer Guide
    • Isaac Nova Orin
    • NVIDIA Isaac ROS
    • NVIDIA Optical Flow SDK
    • Triton Inference Server
    • Accelerated GStreamer
    • Nvida Triton Inference Server tutorial
    • JavaCPP Presets for Triton Inference Server
    • NVIDIA DCGM
  • DeepStream
    • Gst-nvdewarper
    • Deepstream-Dewarper-App
    • DeepStream畸变矫正
    • Managing Video Streams in Runtime with the NVIDIA DeepStream SDK
  • Technical Blog
    • Deploying Your Custom Action Recognition Application
  • AI Toolkit
    • ClearML Setup
    • Track your experiments with ClearML
    • TAO Toolkit v4.0.1 Install
    • ClearML configuration
    • TAO AutoML
    • Spotlight
    • Calculate token/s & GPU memory
  • AutoML
    • 机器学习实验管理 (ML Experiment Management)
    • TAO AutoML
    • microsoft NNI
    • comet.ml
    • AIM An easy-to-use & supercharged open-source AI metadata tracker.
  • IDE Toolkit
    • Lightly Cloud IDE
    • git-lfs
  • Docker
    • Docker tini进程管理器
    • Docker Pull 设置代理
    • TensorFlow Docker安装
  • Utility 实用工具
    • Streamlit Image component https://huggingface.co/spaces/fcakyon/streamlit-image-comparison
    • Image Deduplication with FiftyOne
    • Visualizing Object Detections
    • Managing SSH keys for Github and Gitlab
    • theia-ide develop and deliver with Cloud
    • switch-cuda
    • PyPI配置镜像源
  • C++
    • C++ reference
    • CMake Tutorial
    • CMake Symbols Index
    • Awesome CMake
    • RapidJSON Documentation
    • libevent 编译缺少openssl 原因是没有安装 libssl-dev
  • Java
    • LMAX Disruptor
  • 安全相关
    • Fortify Integration Ecosystem
    • GitLab 集成 Fortify
    • python 文件混淆
  • 常用命令
    • Git 添加第三方项目为子模块
    • Mac Enable Git Tab Autocomplete
  • ROS
    • Jetson install of ROS Noetic
    • 创建你的第一个ROS工作区
    • Docker 和 ROS 指南
    • A Guide to Docker and ROS
    • ROS常用命令

🪄 Guides

  • Web3.0
    • 分布式存储基本概念 bilibili
    • IPFS

📚 Depth Network

  • Paper
    • CVPR2022 有什么值得关注的论文 ?
    • Collections 会议论文集和期刊
    • LORA
    • Computer Vision in the Wild (CVinW)
    • 会议论文集和期刊
    • paper-computer-vision
    • CVPR 2023 论文和开源项目合集(Papers with Code)
    • Image Captioning
  • Formwork
    • kornia
  • playground
    • EditAnything
    • diffusionbee
    • Discover AI Technologies
    • 任务驱动的自治代理
    • 使用接地DINO进行自动图像标记
    • Awesome colab notebooks collection
    • replicate playground Collections
    • A Simple Object Detection App Built Using Streamlit And OpenCV.
  • Learn website
    • roboflow notebooks
    • Prompt Engineering Guide
    • langchain
    • Awesome-Anything
    • AI-Competition-Collections
    • SAHI: Slicing Aided Hyper Inference
    • SAHI: A vision library for large-scale object detection & instance segmentation
    • fine-tuning CLIP Model + Custom Pipeline for Image Similarity
    • Google research
    • OpenMMLabCamp 训练营
    • coding-interview-university
    • Nvidia DeepLearningExamples
    • Pose estimation for AR and Robotics BOP: Benchmark for 6D Object Pose Estimation
  • Computer Vision
    • Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP
    • DINOv2: State-of-the-art computer vision models with self-supervised learning
    • F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models
    • Awesome-Open-Vocabulary-Object-Detection
  • Object Detection
    • TAO Pretrained Object Detection
    • slicing-aided-hyper-inference
    • PaddleDetection实现人流量统计人体检测
    • FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization
  • Re-Identification
  • Action recognition
    • CLIP 模型
    • ActionCLIP
    • 视频动作理解和分类
    • Nvidia Tao Toolkit
    • LangChain
    • Action-Recognition Application with NVIDIA TAO and DeepStream
    • NGC ActionRecognitionNet Model Card
    • Deepstream 3d Action recognition
    • Temporal Segment Networks (TSN)
    • Action Recognition Model Zoo
    • TAO ActionRecognitionNet
    • NVIDIA TAO Body Pose Estimation
    • 基于Paddle的智慧交通预测系统
    • deepstream-bodypose-3d
  • YOLO Series
    • JetsonYolov5
    • YOLOv8 on Jetson
    • DeepStream-Yolo
    • Ultralytics YOLOv8
    • Ultralytics YOLOv8 Modes
    • yolov7
    • yolov7-pose-e2e-trt
    • edgeai-yolov5
    • yolov7-pose
    • edgeyolo
    • yolov7-pose-estimation
  • Segment
    • NVIDA semantic-segmentation
    • Segment Anything in High Quality
    • huggingface/Segment-Anything-Video
    • github/segment-anything-video
    • Prompt-Segment-Anything
    • huggingface/Prompt-Segment-Anything-Demo
  • LLM Zoo
    • Chinese Large Language Model
    • LLM Zoo: democratizing ChatGPT
    • FindTheChatGPTer GPT4开源“平替”
    • Chinese-Vicuna llama+lora方案
    • langchain-ChatGLM 基于本地知识库的 ChatGLM 问答
    • LangChain-ChatGLM-Webui
    • GPT Academic
    • Open LLM Leaderboard
    • MOSS 模型
    • LLaVA: Large Language and Vision Assistant
    • Docker Build ChatGLM-6B
    • 中文大模型集合
    • LLM （大语言模型）整理
    • Chinese-Vicuna
    • haotian-liu/LLaVA
    • Chinese-LLaMA-Alpaca
    • llama-docker-playground
    • LLMsPracticalGuide 大型语言模型实用指南
    • Tuning LLMs
    • 百川智能 Baichaun-7B, Baichuan2-7B
  • Visual Language
    • ViperGPT: Visual Inference via Python Execution for Reasoning
    • vision_language_pretraining.md
    • GLIP Grounded Language-Image Pre-training
    • LLaVA: Large Language and Vision Assistant
  • MultiModal Machine Learning
    • Multi-Source Data Fusion MDPI
  • Paddle
    • PP-YOLOE-SOD 小目标检测模型
    • 输电通道隐患目标检测算法baseline
    • paddledetection readthedocs
    • PaddleYOLO
    • FastDeploy deploy Jetson
  • Text-to-Image Generation
    • GLIGEN: Open-Set Grounded Text-to-Image Generation
    • stable-diffusion-webui
    • stable-diffusion-webui-docker
  • HuggingFace Model Card
    • gpt4-x-alpaca-13b-native-4bit-128g-cuda
    • Open LLM Leaderboard
    • liuhaotian/LLaVA-13b-delta-v0
    • microsoft/visual_chatgpt
    • LLaVA: Large Language and Vision Assistant
    • Visual Instruction Tuning LLaVA: Large Language and Vision Assistant
  • DataSet
    • Waymo autonomous driving
    • waymo challenges
    • imagenet1000_clsidx_to_labels
    • ImageNet Object Localization Challenge 167.62 GB
    • 使用cocotools进行F1-Score评估
    • 重复图片检测 Meta sscd-copy-detection
    • COCO JSON Format with supervision
  • NLP
    • 图解Transformer
    • HanLP
    • 全文索引 分词和搜索
    • Top-AI-Conferences-Paper-with-Code
  • Depth Estimation深度估计
    • depth estimation papers
    • Jetson Inference Depth
  • 天池比赛
    • “阿里灵杰”问天引擎电商搜索算法赛
    • E-commerce-Search-Recall电商搜索召回第二名方案
    • [竞赛] “阿里灵杰”问天引擎电商搜索算法赛 第二名
    • “阿里灵杰”问天引擎电商搜索算法赛
    • Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval
    • FT-Data Ranker: Fine-Tuning Data Processing Competition for LLMs
    • FT-Data Ranker：大语言模型微调数据竞赛 -- 7B模型赛道
  • ONNX
    • A collection of pre-trained, state-of-the-art models in the ONNX format
  • Plate detection
    • Sample app code for LPR deployment on DeepStream deepstream_lpr_app
    • 车牌检测（LPDNet） Model Card
    • License Plate Recognition (LPRNet) Model Card
    • Real-Time License Plate Detection and Recognition App
  • Audio Detection
    • 音频标记的一致组合蒸馏（CED）Consistent Ensemble Distillation for Audio Tagging (CED)
    • Audio-Classification-Deep-Learning using ANN,CNN1D,CNN2D Kaggle Notebook
    • Audio-Classification-Deep-Learning using ANN,CNN1D,CNN2D GitHub
    • Audio Classification Using ANN UrbanSound8K
    • Freesound Audio Tagging 2019
    • Alibaba-MIIL AudioClassfication
    • Bird@Edge Bird Species Recognition at the Edge using NVIDIA Jetson Nano on the EfficientNet-B3
    • BirdClef 2023: Pytorch Lightning-Inference
    • PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition
    • Consistent Ensemble Distillation for Audio Tagging (CED)
    • Pretrained CED on 🤗 Hugging Face
    • Audio Classification, Tagging & Sound Event Detection in PyTorch
    • audio label studio
    • freesound
    • An Introduction to Audio Classification with Keras
  • SfM(Structure-from-Motion)
    • Image Matching Workshop
    • SuperPoint
    • COLMAP - Structure-from-Motion and Multi-View Stereo
  • 3D Reconstruction
    • NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video

❤️ Computer science

  • Algorithm & Data Structure
    • 数据结构考试七天速刷
    • 数据结构和算法
    • [MIT] 6.851: Advanced Data Structures
    • stanford CS166 Data Structures
    • [数据结构]清华大学邓俊辉 数据结构c/c++ Data Structure
    • [MIT]6.006 Introduction To Algorithms
    • [MIT]6.046J Design And Analysis Of Algorithms
    • [MIT]6.851 Advanced Data Structures
    • [MIT]6.851: Advanced Data Structures
  • cs course
    • Stanford CS Curriculum : Stanford CS 课程
    • Stanford公开课筛选
    • CMU CS course
    • UC Berkeley course
    • Computer Science courses with video lectures
    • BiliBili公开课目录
    • Awesome CS Courses
    • UCB CS 61A：计算机程序的结构和解释
    • 计算机公开课推荐
  • Machine Learning
    • [Stanford CS 329S] 机器学习系统设计
    • [Stanford CS 329P] Practical Machine Learning
    • [机器学习] d2l.ai
  • MIT cs course
    • [MIT]6.004: Computation Structures 数字系统设计的基础知识
    • [MIT]6.823: Computer System Architecture 计算机体系结构的设计
  • Other
    • Awesome List
    • 可扩展软件架构 Scalable-Software-Architecture

✏️ Bug Fixed

  • Ubuntu System Error
    • Ubuntu 18.04 LTS - version 'GLIBCXX_3.4.26' not found
    • Nvidia Optical Flow SDK NvOFCudaAPI return error 2
    • 解决Ubuntu终端里面显示路径名称太长
    • Ubuntu Opencv
    • Opencv build Install
    • Reset the SMC of your Mac
    • MacBook Pro (Retina, 15-inch, Mid 2015)电池更换
    • Docker 设置时区
    • libp11-kit.so.0: undefined symbol: ffi_type_pointer, version LIBFFI_BASE_7.0
    • conda环境下pip命令修复
Back to top
Edit this page

Nvidia TAO#

Body Pose Estimation#

将TAO模型集成到DeepStream中

multi-person body pose estimation network

Next
中文语言大模型
Previous
视频理解和行为识别
Copyright © 2023, Kevin
Made with Sphinx and @pradyunsg's Furo
On this page
  • Nvidia TAO
    • Body Pose Estimation