Space to depth layer
A space to depth layer permutes the spatial blocks of the input into the depth dimension. Use this layer when you need to combine feature maps of different size without discarding any feature data.
Given an input feature map of size [M
N
P], the output feature map size is
[floor
(M/height)
floor
(N/width)
P*
height*
width],
where height and width are the specified block
size.
roiMaxPooling2dLayer
| yolov2Layers