← 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 2026-11-14T15:40:56.545Z

Upsampling layers perform the opposite transformation, outputting a tensor that is larger in the spatial dimensions than the input: . One kind of upsampling layer can be made as the analogue of strided convolution. Strided convolution convolves then subsamples; this upsampling layer instead dilates the signal then convolves. Starting with a blank image of zeros, h = 0, we set:

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/c024b.xhtml

EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8