person-detection-0302#
Use Case and High-Level Description#
This is a person detector that is based on Resnet50 backbone with ATSS head for 1280x720 resolution.
Example#
Specification#
Metric |
Value |
---|---|
AP @ [ IoU=0.50:0.95 ] |
0.447 (internal test set) |
GFlops |
370.2079 |
MParams |
51.1641 |
Source framework |
PyTorch* |
Average Precision (AP) is defined as an area under the precision/recall curve.
Inputs#
Image, name: image
, shape: 1, 3, 720, 1280
in the format B, C, H, W
, where:
B
- batch sizeC
- number of channelsH
- image heightW
- image width
Expected color order is BGR
.
Outputs#
The
boxes
is a blob with the shape100, 5
in the formatN, 5
, whereN
is the number of detected bounding boxes. For each detection, the description has the format: [x_min
,y_min
,x_max
,y_max
,conf
], where:(
x_min
,y_min
) - coordinates of the top left bounding box corner(
x_max
,y_max
) - coordinates of the bottom right bounding box corner.conf
- confidence for the predicted class
The
labels
is a blob with the shape100
in the formatN
, whereN
is the number of detected bounding boxes. In case of person detection, it is equal to1
for each detected box with person in it and0
for the background.
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.