Fig. 2
From: Algorithm for pixel-level concrete pavement crack segmentation based on an improved U-Net model
The \(3\times 3\) convolution is transformed into two convolutions of \(1\times 3\) and \(3\times 1\).
Fig. 2 | Scientific Reports
From: Algorithm for pixel-level concrete pavement crack segmentation based on an improved U-Net model
The \(3\times 3\) convolution is transformed into two convolutions of \(1\times 3\) and \(3\times 1\).
