原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
This loss function adapts to the structure of the data and the behavior of the generator to penalize just the relevant errors the generator is currently making. It can help to also add a conventional regression loss, such as the L1 loss, to stabilize the optimization process, yielding the following objective:
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/c034.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8