“…In the training process, the images in the dataset were cropped to the size of the patch image (33,33). The input image size of the CNN model was (33,33), and the size of each convolution kernel was (9,9), so the output feature size was (33−9+1,33-9+1,20) in first layer, which is (25,25,20). The second layer had 10 kernels that were (5,5), so the size of output feature was (25-5+1,25-5+1,10), which is (21,21,10).…”