roi_average_align_2d(x, rois, roi_indices, outsize, spatial_scale, sampling_ratio=None)¶
Spatial Region of Interest (ROI) average align function.
This function acts similarly to
roi_average_pooling_2d(), but it computes average of input spatial patch with bilinear interpolation for each channel with the region of interest.
x (Variable) – Input variable. The shape is expected to be 4 dimensional:
(n: batch, c: channel, h, height, w: width).
rois (Variable) – Input roi variable. The shape is expected to be
(n: data size, 4), and each datum is set as below:
(y_min, x_min, y_max, x_max).
roi_indices (Variable) – Input roi variable. The shape is expected to be
(n: data size, ).
spatial_scale (float) – Scale of the roi is resized.
sampling_ratio ((int, int) or int) – Sampling step for the alignment. It must be an integer over \(1\) or
None, and the value is automatically decided when
Noneis passed. Use of different ratio in height and width axis is also supported by passing tuple of int as
sampling_ratio=(s, s)are equivalent.
- Return type
See the original paper proposing ROIAlign: Mask R-CNN.