Edit this page

instance-segmentation-security-0091

Use Case and High-Level Description

This model is an instance segmentation network for 80 classes of objects. It is a Cascade mask R-CNN with ResNet101 backbone and deformable convolutions, FPN, RPN, detection and segmentation heads.

Example

Specification

Metric

Value

COCO val2017 box AP (max short side 800, max long side 1344)

45.8%

COCO val2017 mask AP (max short side 800, max long side 1344)

39.7%

COCO val2017 box AP (max height 800, max width 1344)

43.55%

COCO val2017 mask AP (max height 800, max width 1344)

38.14%

Max objects to detect

100

GFlops

828.6324

MParams

101.236

Source framework

PyTorch*

Average Precision (AP) is defined and measured according to standard COCO evaluation procedure.

Inputs

Image, name: image, shape: 1, 3, 800, 1344 in the format 1, C, H, W, where:

  • C - number of channels

  • H - image height

  • W - image width

The expected channel order is BGR

Outputs

Model has outputs with dynamic shapes.

  1. Name: labels, shape: -1 - Contiguous integer class ID for every detected object.

  2. Name: boxes, shape: -1, 5 - Bounding boxes around every detected objects in (top_left_x, top_left_y, bottom_right_x, bottom_right_y) format and its confidence score in range [0, 1].

  3. Name: masks, shape: -1, 28, 28 - Segmentation heatmaps for every output bounding box.

Training Pipeline

The OpenVINO Training Extensions provide a training pipeline, allowing to fine-tune the model on custom dataset.

Demo usage

The model can be used in the following demos provided by the Open Model Zoo to show its capabilities:

Prev Next