原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
To handle this it is common to cut off the last layer of the network and replace it with a new final layer that outputs the correct dimensionality. If the input dimensionality changes, you can do the same with the first layer of the network. Both these changes are shown next, in figure 37.2.
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/c037.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8