instance-segmentation-security-1039#
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 |
---|---|
COCO val2017 box AP |
32.9% |
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 COCO evaluation procedure.
Inputs#
Image, name: image
, shape: 1, 3, 480, 480
in the format 1, C, H, W
, where:
C
- number of channelsH
- image heightW
- image width
The expected channel order is BGR
Outputs#
Model has outputs with dynamic shapes.
Name:
labels
, shape:-1
- Contiguous integer class ID for every detected object.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].Name:
masks
, shape:-1, 14, 14
- 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:
Legal Information#
[*] Other names and brands may be claimed as the property of others.