ops_ps_roi_align {torchvisionlib} | R Documentation |
Performs Position-Sensitive Region of Interest (RoI) Align operator
Description
The (RoI) Align operator is mentioned in Light-Head R-CNN.
Usage
ops_ps_roi_align(
input,
boxes,
output_size,
spatial_scale = 1,
sampling_ratio = -1
)
nn_ps_roi_align(output_size, spatial_scale = 1, sampling_ratio = -1)
Arguments
input |
( |
boxes |
( |
output_size |
(int or |
spatial_scale |
(float): a scaling factor that maps the box coordinates to the input coordinates. For example, if your boxes are defined on the scale of a 224x224 image and your input is a 112x112 feature map (resulting from a 0.5x scaling of the original image), you'll want to set this to 0.5. Default: 1.0 |
sampling_ratio |
(int): number of sampling points in the interpolation grid
used to compute the output value of each pooled output bin. If > 0,
then exactly |
Value
Tensor[K, C / (output_size[1] * output_size[2]), output_size[1], output_size[2]]
:
The pooled RoIs
Functions
-
nn_ps_roi_align()
: Thetorch::nn_module()
wrapper forops_ps_roi_align()
.
Examples
if (torchvisionlib_is_installed()) {
library(torch)
library(torchvisionlib)
input <- torch_randn(1, 3, 28, 28)
boxes <- list(torch_tensor(matrix(c(1,1,5,5), ncol = 4)))
roi <- nn_ps_roi_align(output_size = c(1, 1))
roi(input, boxes)
}