RPROIParams is used to create the RPROIPlugin instance.
More...
RPROIParams is used to create the RPROIPlugin instance.
It contains:
- Parameters
-
poolingH | Height of the output in pixels after ROI pooling on feature map. |
poolingW | Width of the output in pixels after ROI pooling on feature map. |
featureStride | Feature stride; ratio of input image size to feature map size. Assuming that max pooling layers in neural network use square filters. |
preNmsTop | Number of proposals to keep before applying NMS. |
nmsMaxOut | Number of remaining proposals after applying NMS. |
anchorsRatioCount | Number of anchor box ratios. |
anchorsScaleCount | Number of anchor box scales. |
iouThreshold | IoU (Intersection over Union) threshold used for the NMS step. |
minBoxSize | Minimum allowed bounding box size before scaling, used for anchor box calculation. |
spatialScale | Spatial scale between the input image and the last feature map. |
◆ poolingH
int32_t nvinfer1::plugin::RPROIParams::poolingH |
◆ poolingW
int32_t nvinfer1::plugin::RPROIParams::poolingW |
◆ featureStride
int32_t nvinfer1::plugin::RPROIParams::featureStride |
◆ preNmsTop
int32_t nvinfer1::plugin::RPROIParams::preNmsTop |
◆ nmsMaxOut
int32_t nvinfer1::plugin::RPROIParams::nmsMaxOut |
◆ anchorsRatioCount
int32_t nvinfer1::plugin::RPROIParams::anchorsRatioCount |
◆ anchorsScaleCount
int32_t nvinfer1::plugin::RPROIParams::anchorsScaleCount |
◆ iouThreshold
float nvinfer1::plugin::RPROIParams::iouThreshold |
◆ minBoxSize
float nvinfer1::plugin::RPROIParams::minBoxSize |
◆ spatialScale
float nvinfer1::plugin::RPROIParams::spatialScale |
The documentation for this struct was generated from the following file: