原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
The key idea of CNNs is to chop up the input image into little patches, and then process each patch independently and identically. The gist of this is captured in figure 24.1:
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/c024b.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8