原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
extending the input image by adding additional pixels so that the output can have the same size as the input. So, for a kernel with support [–N, N] × [–M, M], one has to add N/2 additional pixels left and right of the image and M/2 pixels at the top and bottom. Then, the output will have the same size as the original input image.
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c015b.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8