原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
This network has one convolutional layer with C channels followed by a relu layer. The next layer performs spatial global average pooling (gap), and each channel gets projected into a single number that contains the sum of the outputs of the relu. This results in a representation given by a vector of length C. This vector is then processed by a fully connected layer (fc).
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