NGC | Catalog
Welcome Guest
CatalogModelsMaskRCNN TF2 checkpoint (AMP)

MaskRCNN TF2 checkpoint (AMP)

For downloads and more information, please view on a desktop device.
Logo for MaskRCNN TF2 checkpoint (AMP)

Description

MaskRCNN TensorFlow2 checkpoint trained with AMP

Publisher

NVIDIA Deep Learning Examples

Use Case

Segmentation

Framework

TensorFlow2

Latest Version

21.02.0

Modified

October 29, 2021

Size

338.39 MB

Model Overview

Mask R-CNN is a convolution based network for object instance segmentation.

Model Architecture

Mask R-CNN builds on top of Faster R-CNN adding a mask head for the task of image segmentation.

The architecture consists of the following:

  • ResNet-50 backbone with Feature Pyramid Network (FPN)
  • Region proposal network (RPN) head
  • RoI Align
  • Bounding and classification box head
  • Mask head

Architecture

Figure 1. Diagram of Mask R-CNN framework from original paper

Training

This model was trained using script available on NGC and in GitHub repo

Dataset

The following datasets were used to train this model:

  • COCO 2017 - Dataset for large-scale object detection, segmentation and captioning.

Performance

Performance numbers for this model are available in NGC

References

License

This model was trained using open-source software available in Deep Learning Examples repository. For terms of use, please refer to the license of the script and the datasets the model was derived from.