Research on Image Super-Resolution Reconstruction Technology Based on Unsupervised Learning

Table 1

Generate network parameters.

Network layer	Input feature (, , )	Convolutional layer parameters (, , , )	Output feature (, , )
Conv1	(1, 64, 64)	(4, 64, 2, 1)	(64, 32, 32)
Conv2	(64, 32, 32)	(3, 64, 1, 1)	(64, 32, 32)
Conv3	(64, 32, 32)	(3, 64, 1, 1)	(64, 32, 32)
Conv4	(64, 32, 32)	(1, 64, 1, 0)	(64, 32, 32)
Conv5	(64, 32, 32)	(1, 64, 1, 0)	(64, 32, 32)
Conv6	(64, 32, 32)	(1, 1, 1, 0)	(1, 32, 32)