TAO Pretrained Instance Segmentation

TAO Pretrained Instance Segmentation

Logo for TAO Pretrained Instance Segmentation
Pretrained weights to facilitate transfer learning using TAO Toolkit.
Latest Version
July 25, 2023
38.31 MB

What is Train Adapt Optimize (TAO) Toolkit?

Train Adapt Optimize (TAO) Toolkit is a python based AI toolkit for taking purpose-built pre-trained AI models and customizing them with your own data. TAO adapts popular network architectures and backbones to your data, allowing you to train, fine tune, prune and export highly optimized and accurate AI models for edge deployment.

The pre-trained models accelerate the AI training process and reduce costs associated with large scale data collection, labeling, and training models from scratch. Transfer learning with pre-trained models can be used for AI applications in smart cities, retail, healthcare, industrial inspection and more.

Build end-to-end services and solutions for transforming pixels and sensor data to actionable insights using TAO, DeepStream SDK and TensorRT. The models are suitable for object detection, classification and segmentation.

Instance Segmentation Using TAO

Instance segmentation is a popular computer vision technique that can identify each instance of multiple objects in a frame at the pixel level. Instance segmentation will not only produce bounding boxes around the object, but also segmentation masks. This model card contains pretrained weights that may be used as a starting point with the following instance segmentation networks in Train Adapt Optimize (TAO) Toolkit to facilitate transfer learning.

Following instance segmentation architecture are supported:

  • MaskRCNN

The pre-trained weights are trained on a subset of the Google OpenImages dataset. Following backbones are supported with these MaskRCNN networks.

  • resnet10/resnet18/resnet34/resnet50/resnet101

To see the full list of all the backbones, scroll over to the version history tab.

Note: These are unpruned models with just the feature extractor weights, and may not be used without re-training in an Instance segmentation application

Training Instance Segmentation Models Using TAO

The instance segmentation apps in TAO expect data in COCO format. TAO provides a simple command line interface to train a deep learning model for instance segmentation.

The models in this model area are only compatible with TAO Toolkit. For more information about using this model with TAO, please view the instructions here to install the TAO Launcher CLI and use with the instance segmentation trainer in TAO.

  1. Install the NGC CLI from ngc.nvidia.com

  2. Configure the NGC CLI using the following command

ngc config set
  1. To view all the backbones that are supported by Instance segmentation architecture in TAO:

    ngc registry model list nvidia/tao/pretrained_instance_segmentation:*
  2. Download the model:

    ngc registry model download-version nvidia/tao/pretrained_instance_segmentation:<template> --dest <path>

Instructions to run the sample notebook

  1. Get the NGC API key from the SETUP tab on the left. Please store this key for future use. Detailed instructions can be found here

  2. Configure the NGC command line interface using the command mentioned below and follow the prompts.

ngc config set
  1. Download the sample notebooks from NGC using the command below
ngc registry resource download-version "nvidia/tao_cv_samples:v1.0.2"
  1. Invoke the jupyter notebook using the following command

    jupyter notebook --ip --port 8888 --allow-root
  2. Open an internet browser and type in the following URL to start running the notebooks when running on a local machine.

    If you wish to run view the notebook from a remote client, please modify the URL as follows:


    Where, the a.b.c.d is the IP address of the machine running the container.

Other TAO Pre-trained Models


This work is licensed under the Creative Commons Attribution 4.0 International License. To view a copy of this license, please visit this link, or send a letter to Creative Commons, PO Box 1866, Mountain View, CA 94042, USA.

Technical blogs

Suggested reading

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.