|
TensorRT
|
The Region plugin layer performs region proposal calculation: generate 5 bounding boxes per cell (for yolo9000, generate 3 bounding boxes per cell). For each box, calculating its probablities of objects detections from 80 pre-defined classifications (yolo9000 has 9416 pre-defined classifications, and these 9416 items are organized as work-tree structure). RegionParameters defines a set of parameters for creating the Region plugin layer. More...
#include <NvInferPlugin.h>
Public Attributes | |
| int * | leaf |
| int | n |
| int * | parent |
| int * | child |
| int * | group |
| char ** | name |
| int | groups |
| int * | groupSize |
| int * | groupOffset |
The Region plugin layer performs region proposal calculation: generate 5 bounding boxes per cell (for yolo9000, generate 3 bounding boxes per cell). For each box, calculating its probablities of objects detections from 80 pre-defined classifications (yolo9000 has 9416 pre-defined classifications, and these 9416 items are organized as work-tree structure). RegionParameters defines a set of parameters for creating the Region plugin layer.
| num | Number of predicted bounding box for each grid cell. |
| coords | Number of coordinates for a bounding box. |
| classes | Number of classfications to be predicted. |
| softmaxTree | When performing yolo9000, softmaxTree is helping to do softmax on confidence scores, for element to get the precise classfication through word-tree structured classfication definition. |