← 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

where k × k is the patch size. Notice that this operation is equivalent to the sliding window action of CNN, so can simply be implemented as a CNN that outputs a 2 × N × M feature map of real-versus-synthetic scores. Naturally, patches can be sampled at different strides and resolutions, depending on the exact architecture of the CNN .

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