TLT 2.0
  • Achieve 2x inference speedup with INT8 precision while maintaining comparable to FP16/FP32 using quantization aware training
  • Speedup training time and save on memory bandwidth with automatic mixed precision running on Tensor Cores for NVIDIA Volta and Turing GPUs
  • Introducing highly accurate purpose-built models:
  • PeopleNet
  • TrafficCamNet
  • DashCamNet
  • FaceDetect-IR
  • VehicleTypeNet
  • VehicleMakeNet
  • Train with popular networks: YOLOV3, RetinNet, DSSD, FasterRCNN, DetectNet_v2, MaskRCNN and SSD
  • Out of the box compatibility with DeepStream SDK 5.0
  • Avoid models overfitting on training data and drastically increase the training dataset by applying common augmentation techniques such as rotation, zoom, cropping, color augmentation. This is very useful when collecting large dataset is expensive or difficult

Operating System
  • Ubuntu 18.04
  • Driver version >= 440
  • Docker-ce > 18.09
  • nvidia-docker2

Getting Started Resources

Next version of Transfer Learning Toolkit with support for conversational AI models will be available in early 2021. Sign up to be notified on general availability.

Downloads Available on NGC

Documentation & Forums

Blogs & Tutorials

Community Projects

  • Take a look at our innovative developer community projects and submit your cool project to be featured on our community project hub


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.