Bodypose Estimation using TAO BodyposeNet

BodyPoseNet is an NVIDIA-developed multi-person body pose estimation network included in the TAO Toolkit. It aims to predict the skeleton for every person in a given input image, which consists of keypoints and the connections between them. BodyPoseNet follows a single-shot, bottom-up methodology, so there is no need for a person detector. The pose/skeleton output is commonly used as input for applications like activity/gesture recognition, fall detection, and posture analysis, among others.

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.

Bodypose Estimation using TAO BodyposeNet

In this jupyter notebook, you will learn how to leverage the simplicity and convenience of TAO to:

1. Train a Bodypose Estimation model on the Common Objects in Context (COCO) dataset
2. Evaluate the model's performance
3. Run Inference on the trained model
4. Prune and re-train the pruned model
5. Export the model to a .etlt file for deployment to DeepStream SDK
6. Optimize the standard fp32 model into an int8 TensorRT Engine for optimized deployment for the system GPU

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 One Click 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.

*Note: A customized kernel for the Jupyter Notebook is used as the primary mechanism for deployment. This kernel has been built on the TAO Toolkit container.