← 返回卡片

原书出处

Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)

核验版本的摘录快照 · 导入于 2026-11-14T15:40:56.565Z

Thinking of dϕ as a learned loss function raises new questions: What does this loss function penalize, and how can we control its properties. One of the main levers we have is the architecture of dϕ; different architectures will have the capacity, and/or inductive bias, to penalize different kinds of errors. One popular architecture for image-to-image tasks is a PatchGAN discriminator [232], in which we

此预览只包含定位所需的摘录和上下文。

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