Table 1.

Detailed parameters of the CNN network.

Block	Layer	Kernel size	Stride	Pad	Output size
Input Data	-	-	-	-	144∗144∗1
Conv-Relu 1	Conv1	5	1	2	144∗144∗80
	Relu1	-	-	-	144∗144∗80
Pool-Conv-Relu 1	Pool1	2	2	-	72∗72∗80
	Conv2	5	1	2	72∗72∗120
	Relu2	-	-	-	72∗72∗120
Pool-Conv-Relu 2	Pool2	2	2	-	36∗36∗120
	Conv3	9	1	4	36∗36∗500
	Relu3	-	-	-	36∗36∗500
Conv-Relu 2	Conv4	1	1	0	36∗36∗300
	Relu4	-	-	-	36∗36∗300
Conv-Relu 3	Conv5	3	1	1	36∗36∗100
	Relu5	-	-	-	36∗36∗100
Conv-Relu 4	Conv6	3	1	1	36∗36∗1
	Relu6	-	-	-	36∗36∗1
Deconv1	Deconv1	4	2	1	72∗72∗1
Concatenate1	Concat1	-	-	-	72∗72∗121
Conv-Relu 5	Conv7	1	1	0	72∗72∗1
	Relu7	-	-	-	72∗72∗1
Deconv2	Deconv2	4	2	1	144∗144∗1
Concatenate2	Concat2	-	-	-	144∗144∗81
Conv6	Conv8	1	1	0	144∗144∗1
Output	Flatten1	-	-	-	144∗144∗1