Skip to main content
. 2024 Aug 10;14:18619. doi: 10.1038/s41598-024-69827-0

Figure 4.

Figure 4

Attention block. H, W, and C represent the height, width, and number of channels of the input feature map, respectively; P denotes the patch size for calculating attention; FFN refers to a feed-forward neural network with two hidden layers.