chainer.functions.roi_average_align_2d¶
-
chainer.functions.
roi_average_align_2d
(x, rois, roi_indices, outsize, spatial_scale, sampling_ratio=None)[source]¶ Spatial Region of Interest (ROI) average align function.
This function acts similarly to
ROIPooling2D
, but it computes average of input spatial patch with bilinear interpolation for each channel with the region of interest.Parameters: - x (Variable) – Input variable. The shape is expected to be
4 dimentional:
(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, )
. - outsize ((int, int) or int) – Expected output size after pooled
(height, width).
outsize=o
andoutsize=(o, o)
are equivalent. - 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 whenNone
is passed. Use of different ratio in height and width axis is also supported by passing tuple of int as(sampling_ratio_h, sampling_ratio_w)
.sampling_ratio=s
andsampling_ratio=(s, s)
are equivalent.
Returns: Output variable.
Return type: See the original paper proposing ROIAlign: Mask R-CNN.
- x (Variable) – Input variable. The shape is expected to be
4 dimentional: