TAO

Introduction

• Overview

Migration Guides

• Migration Guides
  • Migrating to TAO 7.0
  • Migrating to TAO 6.0
  • Migrating to TAO 5.5
  • Migrating to the TAO API from TAO 5.3.0
  • Migrating from TAO 4.0.x to TAO 5.0.0
  • Migrating from TAO 3.x to TAO 4.0
  • Migrating from Legacy TLT to TAO

Getting Started

• Getting Started with NVIDIA TAO Toolkit

Model Zoo

• Overview
• Foundation Models

Dataset

• Data Annotation Format
  • Image Classification Format
  • Optical Inspection Format
  • Multiple Golden VisualChangeNet Classification Format
  • Change Detection (Segmentation) Format
  • CenterPose Format
  • Image Classification Format PyTorch
  • Object Detection – KITTI Format
  • Object Detection – COCO Format
  • Open Vocabulary Object Detection/Segmentation – ODVG Format
  • Instance Segmentation – COCO format
  • Semantic Segmentation - PNG Mask Format
  • Gesture Recognition – Custom Format
  • Heart Rate Estimation – Custom Format
  • EmotionNet, FPENET, GazeNet – JSON Label Data Format
  • BodyposeNet – COCO Format
  • Re-Identification – Market-1501 Format
  • Sparse4D Detection & Tracking – OVPKL Format
• Data Services
  • Annotations
  • Offline Data Augmentation
  • Auto-Label
  • Data Analytics

Embedding Model Fine-tuning

• Embedding Model Fine-Tuning
  • Supported Models

VLM Model Fine-tuning

• Vision-Language Model (VLM) Fine-Tuning
  • Supported Models
  • Key Features
  • Getting Started

CV Model Fine-tuning

• Optimizing the Training Pipeline and Models
  • Knowledge Distillation
  • Automatic Mixed Precision
  • Model Pruning
  • Quantization Aware Training
  • Post-Training Quantization
• Visualizing Training
  • Enabling TensorBoard During Training
  • Visualizing using TensorBoard
  • Additional Resources
• Computer Vision Finetuning
  • PyTorch
  • TensorFlow 2.x [Deprecated]
  • TensorFlow 1.x [Deprecated]
• AutoML
  • AutoML Algorithm Explanation
  • Prerequisites
  • Running AutoML from Your Agent
  • Getting Started
  • AutoML Outcomes
• Quantizing a model in TAO (TAO Quant)
  • Quantization at a Glance
  • Weight-Only vs Weights+Activations
  • TAO Quant Vision
  • Choosing a Backend
  • Quick Start
  • What’s Supported
  • Dive Deeper
  • Workflows

MLOPS integration

• Overview
• TAO WandB Integration
  • Quick Start
  • Visualization output
• TAO Clearml Integration
  • Quick Start
  • Visualization Output

Deploying to Inference SDKs

• TAO Deploy Overview
  • Driving TAO Deploy from the Agent
  • Specification Format
  • NSight DL Designer Integration
  • Per-Network Notes
• Integrating TAO CV Models with Triton Inference Server
  • Driving Triton Deployment from the Agent
• Optimizing and Profiling with TensorRT
  • TRTEXEC with ActionRecognitionNet
  • TRTEXEC with BodyPoseNet
  • TRTEXEC with CenterPose
  • TRTEXEC with CLIP
  • TRTEXEC with Classification TF1/TF2/PyT
  • TRTEXEC with Deformable-DETR
  • TRTEXEC with DetectNet-v2
  • TRTEXEC with DINO
  • TRTEXEC with DSSD
  • TRTEXEC with EfficientDet TF1/TF2
  • TRTEXEC with Facial Landmarks Estimation
  • TRTEXEC with Faster RCNN
  • TRTEXEC with Grounding DINO
  • TRTEXEC with LPRNet
  • TRTEXEC with MAE
  • TRTEXEC with Metric Learning Recognition
  • TRTEXEC with Mask RCNN
  • TRTEXEC with Multitask Classification
  • TRTEXEC with OCDNet
  • TRTEXEC with OCRNet
  • TRTEXEC with PointPillars
  • TRTEXEC with PoseClassificationNet
  • TRTEXEC with ReIdentificationNet
  • TRTEXEC with ReIdentificationNet Transformer
  • TRTEXEC with RetinaNet
  • TRTEXEC with RT-DETR
  • TRTEXEC with Segformer
  • TRTEXEC with SiameseOI
  • TRTEXEC with SSD
  • TRTEXEC with UNet
  • TRTEXEC with YOLO_v3
  • TRTEXEC with YOLO_v4
  • TRTEXEC with YOLO_v4_tiny
  • TRTEXEC with VisualChangeNet
  • TRTEXEC with Mask2former
  • TRTEXEC with Mask Grounding DINO
• Integrating TAO Models into DeepStream
  • Installation Prerequisites
  • Deployment Files
  • Sample Application
  • Image classification
  • Multitask Classification
  • Object Detection
  • Instance Segmentation
  • Semantic Segmentation
  • Character Recognition Using nvOCDR

More Information

• Release Notes
  • Version list
  • TAO 7.0.1
  • TAO 7.0
  • TAO 6.26.3
  • TAO 6.25.11
  • TAO 6.25.10
  • TAO 6.25.09
  • TAO 6.25.7
  • TAO 6.0.0
  • TAO 5.5.0
  • TAO 5.3.0
  • TAO 5.2.0
  • TAO 5.1.0
  • TAO 5.0.0
  • TAO 4.0.2
  • TAO 4.0.1
  • TAO 4.0.0
  • TAO 3.0-22.05
  • TAO 3.0-22.02
  • TAO 3.0-21.11
  • TAO 3.0-21.08
• Frequently Asked Questions
  • Installation and Usage
  • Model support
  • Pruning
  • Model Export and Deployment
  • Training
• Troubleshooting Guide
  • NGC
  • Agent and Plugin Issues
• Tutorial Videos
  • Getting started with NVIDIA TAO
  • Create Custom Multi-Modal Fusion Models
  • Use Visual Prompt for In-Context Segmentation with NVIDIA TAO
  • Estimate and Track Object Poses with the NVIDIA TAO FoundationPose Model
  • Open Vocabulary Object Detection with NVIDIA Grounding-DINO
  • Use Text Prompts for Auto-Labeling with NVIDIA TAO
  • Visualize Model Training with TensorBoard
• Support Information
• Acknowledgements
  • nitime
  • OpenSSL
  • JsonCpp
  • Python
  • libcurl
  • OpenCV
  • zlib
  • TensorFlow
  • Keras
  • PyTorch
  • ssd_keras
  • Yamale
  • PyCUDA
  • protobuf
  • onnx
  • PIL
  • PyYAML
  • addict
  • argcomplete
  • bto3
  • cryptography
  • docker
  • dockerpty
  • gRPC
  • h5py
  • jupyter
  • numba
  • numpy
  • pandas
  • posix_ipc
  • prettytable
  • arrow
  • PyJWT
  • requests
  • retrying
  • seaborn
  • scikit-image
  • scikit-learn
  • semver
  • Shapely
  • simplejson
  • six
  • python-tabulate
  • toposort
  • tqdm
  • uplink
  • xmltodict
  • recordclass
  • cocoapi
  • mpi4py
  • Open MPI
  • lazy_object_proxy
  • onnxruntime
  • pytorch-lightning
  • KenLM
  • Eigen
  • google/automl
  • open-mmlab/OpenPCDet
  • VainF/Torch-Pruning
  • gmalivenko/onnx2keras
  • open-mmlab/mmskeleton
  • NVIDIA Synthetic Dataset License Agreement