Skip to main content
. 2020 Dec 8;14:592352. doi: 10.3389/fnins.2020.592352

Figure 3.

Figure 3

Pictorial view of efficient implementation of cross-hair filters. Grayscaled stacks refer to input to the layer, red shaped squares refer to 2-D kernels used for each plane. Brown colored slices refer to extracted features after convolution operations and + symbol refers to matrix addition.