Open CaiShilv opened 1 year ago
It is a great honor to see your work. I would like to ask why the decoder output is the residual instead of getting the reconstructed image directly.
我觉得吧,当然可以是直接输出了结果了。你自己训练一遍就行。
Yes, you can also train the model to output the image directly. We find that predicting residual can lead to better results, and this is why we adopt residual learning.
It is a great honor to see your work. I would like to ask why the decoder output is the residual instead of getting the reconstructed image directly.