TLT 3.0
-
Highlights:
- New purpose-built pretrained models for computer vision:
- Emotion recognition
- Facial landmark
- License plate detection and recognition
- Heart rate estimation
- Gesture recognition
- Gaze estimation
- People segmentation
- Introducing ASR and NLP models with inference samples for:
- Named Entity Recognition (NER)
- Question/Answering
- Punctuation
- Text classification
- TLT 3.0 brings support for NVIDIA Ampere GPUs with third generation tensor core additions and various performance optimizations
- Improved PeopleNet model to detect difficult scenarios such as people sitting down, rotated/ warped objects
- Quickly kickstart training models with the hassle free TLT launcher tool for pulling compatible containers to initialize
- Train with popular networks: EfficientNet, ResNet, YOLOV3/V4, FasterRCNN, SSD, DetectNet_v2, MaskRCNN and UNET
- Out of the box compatibility with DeepStream SDK for vision AI deployment
- Out of the box compatibility with Jarvis for conversational AI deployment
- Enable faster training with jobs split up across multi-GPUs
Share TLT and AI models update with your network:
Developer news article for computer vision
Developer news article for conversational AI
Operating System |
|
---|---|
Dependencies |
|
Latest Product News

Developer Tutorial
Learn how to build and deploy conversational AI models using the NVIDIA Transfer Learning Toolkit.

Developer Tutorial
Learn how to train State-Of-The-Art Models for classification and object detection.

Developer Tutorial
Learn how to create a real-time number plate detection and recognition app.

Developer Webinar
Learn how to create a gesture recognition application with robot interactions.
Getting Started Resources
Conversational AI
- TLT conversational AI models and container collection: Download from NGC
- To deploy with Jarvis, go to download resources
- Get started with Jupyter Notebooks:
Vision AI
- TLT computer vision models and container collection: Download from NGC
- Collection of Jupyter Notebooks and training specs for vision AI model
- To deploy TLT models using DeepStream, go to download resources
- DeepStream sample apps to deploy YoloV3/V4, FasterRCNN, UNET, etc.
- Models trained with TLT Sample App for license plate detection and recognition using DeepStream
- Sample App for Gaze estimation, Facial Landmark, HeartRateNet, Gesture and Emotion - x86 | Jetson
- To convert TLT model (etlt) to TensorRT engine for deployment with DeepStream, select the appropriate
tlt-converter
for your hardware and software stack.
Platform | Compute | Download |
---|---|---|
x86 + GPU | CUDA 10.2 / cuDNN 8.0 / TensorRT 7.1 | Download |
x86 + GPU | CUDA 10.2 / cuDNN 8.0 / TensorRT 7.2 | Download |
x86 + GPU | CUDA 11.0 / cuDNN 8.0 / TensorRT 7.1 | Download |
x86 + GPU | CUDA 11.0 / cuDNN 8.0 / TensorRT 7.2 | Download |
x86 + GPU | CUDA 11.1 / cuDNN 8.0 / TensorRT 7.2 | Download |
Jetson | Jetpack 4.4 | Download |
Jetson | Jetpack 4.5 | Download |
Documentation
Developer Forums
- Post your questions or feedback in the following associated forums:
Blogs & Tutorials
- Implementing a Real-time, AI-Based, Face Mask Detector Application for COVID-19
- Improving INT8 accuracy using Quantization Aware Training and NVIDIA Transfer Learning Toolkit
- Developer Tutorial: Training Instance Segmentation Models using MaskRCNN on NVIDIA Transfer Learning Toolkit
- Using the NVIDIA Isaac SDK Object Detection Pipeline with Docker and the NVIDIA Transfer Learning Toolkit
- Building Intelligent Video Analytics Apps Using NVIDIA DeepStream 5.0
- How To Train with Custom Pre-Trained Models using Transfer Learning Toolkit
- What is transfer learning?
- Build and Deploy Accurate Deep Learning Models for Intelligent Image and Video Analytics
- Pruning models with NVIDIA Transfer Learning Toolkit
Community Projects
- Take a look at our innovative developer community projects and submit your cool project to be featured on our community project hub
Webinars
- GTC 2020: Accelerating Vision AI Applications Using NVIDIA Transfer Learning Toolkit and Pre-Trained Models
- GTC 2020: NVIDIA Tools to Train, Build, and Deploy Intelligent Vision Applications at the Edge
- Accelerating deep learning training using NVIDIA Transfer Learning Toolkit
- Real-time object detection for disaster response
- DeepStream SDK- Accelerating Real-Time AI Based Video And Image Analytics
Free Self-Paced DLI Online Courses
- Learn how to build end-to-end intelligent video analytics pipelines using DeepStream and Jetson Nano >> Enroll now
- Learn how to get started with AI using Jetson Nano >> Enroll now
Ethical AI
NVIDIA’s platforms and application frameworks enable developers to build a wide array of AI applications. Consider potential algorithmic bias when choosing or creating the models being deployed. Work with the model’s developer to ensure that it meets the requirements for the relevant industry and use case; that the necessary instruction and documentation are provided to understand error rates, confidence intervals, and results; and that the model is being used under the conditions and in the manner intended.