原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
where the softmax is taken within each row (i.e., over the vector of matches for each separate query vector, like in equation (26.14)). In expanded detail, here are the full mechanics of a self-attention layer (figure 26.10):
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/c026.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8