NGC | Catalog
Welcome Guest
CatalogResourcesTAO Object Detection

TAO Object Detection

For downloads and more information, please view on a desktop device.
Logo for TAO Object Detection

Description

This notebook shows an example usecase of DSSD object detection using Train Adapt Optimize (TAO) Launcher.

Publisher

NVIDIA

Use Case

Other

Framework

Other

Latest Version

v1

Modified

September 13, 2022

Compressed Size

2 MB

Object Detection using TAO DSSD

This notebook shows an example usecase of DSSD object detection using Train Adapt Optimize (TAO) Launcher. In this notebook, you will learn how to leverage the simplicity and convenience of TAO to:

  • Take a pretrained resnet18 model and train a ResNet-18 DSSD model on the KITTI dataset
  • Prune the trained DSSD model
  • Retrain the pruned model to recover lost accuracy
  • Export the pruned model
  • Quantize the pruned model using QAT
  • Run Inference on the trained model

    About Quick Deploy

    The quick deploy feature automatically sets up the Vertex AI instance with an optimal configuration, preloads the dependencies, runs the software from NGC without any need to set up the infrastructure.

    Get Started with Training

    To help you get started, we have created a sample Jupyter Notebook that can be easily deployed on Vertex AI using NGC’s quick deploy feature. This feature automatically sets up the Vertex AI instance with an optimal configuration, preloads the dependencies, runs the software from NGC without any need to set up the infrastructure.

Simply click on the button that reads “Deploy to Vertex AI” and follow the instructions.