marnie007

数据处理

5

为什么hr那里就需要插值，不是就下采样后再进行插值作为输入吗，那里训练集的处理不太懂

数据处理

1

所以你这里输入的是用高斯模糊处理的图像是吗，本应该是插值的是吗

α_in

2

In training step 1, we keep α_in= 0, while in training step 2, we keep α_in = 1. But in the paper , the experiment use different α_in from 0...

Bad result

2

Bad result when I test a image use the EDSR_x* model, but can got right one when use EDSR_baseline model,I dont know the reason, can you help me ?

On super-resolution tasks, the ordinary convolutional layer is replaced by octave convolution, but the loss and calculation time become larger, what is the matter?