Transfer Learning Toolkit

Introduction

• Overview
  • NVIDIA Transfer Learning Toolkit
  • Pre-trained Models
  • TLT Workflow Overview
• Requirements and Installation
  • Hardware Requirements
  • Software Requirements
  • Installation Prerequisites
  • Installation
• Open Model Architectures
  • Model Requirements
• Purpose-Built Models
  • Computer Vision
  • Conversational AI
• Optimizations to the Training Pipeline
  • Quantization Aware Training
  • Automatic Mixed Precision
• TLT Launcher
  • Software Requirements
  • Installing the launcher
  • Running the launcher
• Getting Started With TLT
  • 1. Prerequisites
  • 2. Download Jupyter Notebook
  • 3. Start Jupyter Notebook
  • 4. Train the Model
• Deepstream - TLT Integration
  • Prerequisites
  • Deployment files
  • Sample Application : License Plate Detection and Recognition
  • Resources
• Integrating TLT Trained Models to Jarvis
• Migrating to TLT 3.0

Computer Vision

• Image Classification
  • Preparing the Input Data Structure
  • Creating an Experiment Spec File - Specification File for Classification
  • Training the model
  • Evaluating the Model
  • Running Inference on a Model
  • Pruning the Model
  • Re-training the Pruned Model
  • Exporting the model
  • Deploying to DeepStream
• Object Detection
  • Offline Data Augmentation
  • Data Input for Object Detection
  • DetectNet_v2
  • FasterRCNN
  • YOLO_v3
  • YOLOv4
  • SSD
  • DSSD
  • RetinaNet
• Instance Segmentation
  • Data Input for Instance Segmentation
  • MaskRCNN
  • Exporting the Model
  • Deploying to DeepStream
• Semantic Segmentation
  • Data Input for Semantic Segmentation
  • UNET
• Labeling Data Format
  • Json Label Data Format
• Emotion Classification
  • Pre-processing the Dataset
  • Creating an Experiment Specification File
  • Training the Model
  • Evaluating the Model
  • Run Inference on the Model
  • Deploying to the TLT CV Inference Pipeline
• Gaze Estimation
  • Pre-processing the Dataset
  • Creating an Experiment Specification File
  • Training the Model
  • Evaluating the Model
  • Run Inference on the Model
  • Deploying to the TLT CV Inference Pipeline
• Character Recognition
  • LPRNet
• Facial Landmarks Estimation
  • Facial Landmarks
  • Dataset Preparation
  • Creating an Experiment Spec file
  • Training the model
  • Evaluating the model
  • Inference of the model
  • Exporting the model
  • Deploying to the TLT CV Inference Pipeline
• Gesture Recognition
  • Pre-processing the Dataset
  • Creating a Configuration File
  • Training the Model
  • Evaluating the Model
  • Running Inference on the Model
  • Exporting the Model
  • Deploying to the TLT CV Inference Pipeline
• Heart Rate Estimation
  • Data Input for Heart Rate Estimation
  • HeartRateNet Data Format
  • Creating a Configuration File
  • Generating TFRecords
  • Two Branch Network
  • Creating a Configuration File
  • Training the Model
  • Evaluating the Model
  • Running Inference on the Model
  • Exporting the Model
• PeopleNet
  • Training algorithm
  • Intended use case

TLT Computer Vision Inference Pipeline

• Overview
• Requirements and Installation
  • Hardware Requirements
  • Software Requirements
  • Installation Prerequisites
  • Installation
• TLT CV Inference Pipeline Quick Start Scripts
  • Configuring
  • Initialization
  • Launching The Server and Client containers
  • Stopping
  • Cleaning
  • Integration with TLT
• Running and Building Sample Applications
  • TLT CV Inference Pipelines
  • Performance
  • Running the Body Pose Estimation Sample
  • Running the Emotion Classification Sample
  • Running the Face Detection Sample
  • Running the Facial Landmarks Estimation Sample
  • Running the Gaze Estimation Sample
  • Running the Gesture Classification Sample
  • Running the Heart Rate Estimation Sample
  • Building the Sample Applications

Conversational AI

• ASR
  • Speech Recognition
• Natural Language Processing
  • Joint Intent and Slot Classification
  • Punctuation and Capitalization
  • Question Answering
  • Text Classification
  • Token Classification (Named Entity Recognition)

More Information

• Release Notes
  • Transfer Learning Toolkit V3.0
• Frequently Asked Questions
  • Model support
  • Pruning
  • Model Export and Deployment
  • Training