instance-segmentation-security-0050

标签：heatmap   red   mode   amp   precision   put   RoCE   instance   tor   

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 ResNet50 backbone, FPN and Bottom-Up Augmentation blocks and light-weight RPN.

Example

Specification

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

Performance

Inputs

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

1. name: im_info, shape: [1x3] - Image information: processed image height, processed image width and processed image scale w.r.t. the original image resolution.

Outputs

1. name: classes, shape: [100, ] - Contiguous integer class ID for every detected object, ‘0‘ for background, i.e. no object.

1. name: scores: shape: [100, ] - Detection confidence scores in range [0, 1] for every object.

1. name: boxes, shape: [100, 4] - Bounding boxes around every detected objects in (top_left_x, top_left_y, bottom_right_x, bottom_right_y) format.

1. name: raw_masks, shape: [100, 81, 28, 28] - Segmentation heatmaps for all classes for every output bounding box.

Legal Information

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

instance-segmentation-security-0050

标签：heatmap   red   mode   amp   precision   put   RoCE   instance   tor   

原文地址：https://www.cnblogs.com/cloudrivers/p/11870073.html