Use Case and High-Level Description

This model is an instance segmentation network for 80 classes of objects. It is a Mask R-CNN with EfficientNet-B2 backbone, light-weight FPN, RPN, detection and segmentation heads.

Example

Specification

Metric	Value
MS COCO val2017 box AP	32.9%
MS COCO val2017 mask AP	28.6%
Max objects to detect	100
GFlops	13.9672
MParams	10.5674
Source framework	PyTorch*

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

Inputs

name: image , shape: [1x3x480x480] - An input image in the format [1xCxHxW]. The expected channel order is BGR.

Outputs

name: labels, shape: [100] - Contiguous integer class ID for every detected object.
name: boxes, shape: [100, 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].
name: masks, shape: [100, 14, 14] - Segmentation heatmaps for every output bounding box.

Legal Information

[*] Other names and brands may be claimed as the property of others.