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.
|MS COCO val2017 box AP||32.9%|
|MS COCO val2017 mask AP||28.6%|
|Max objects to detect||100|
Average Precision (AP) is defined and measured according to standard MS COCO evaluation procedure.
image, shape: [1x3x480x480] - An input image in the format [1xCxHxW]. The expected channel order is BGR.
labels, shape:  - Contiguous integer class ID for every detected object.
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].
masks, shape: [100, 14, 14] - Segmentation heatmaps for every output bounding box.
[*] Other names and brands may be claimed as the property of others.