In my thougnt,the in_channel and out_channel should be same in UNet,
but in x4-upscaling.yaml
I think this use the latent low_scale_noise (3 channels) and the img(4 channels),so it has 7 in_channels,
but I am confused about how in_channel can be convert to out_channel,it there some method in low_sample?
I am trying to read the code, but i got nothing.
Can somboby has a different thought about that,it will help me a lot!!
In my thougnt,the in_channel and out_channel should be same in UNet, but in x4-upscaling.yaml
I think this use the latent low_scale_noise (3 channels) and the img(4 channels),so it has 7 in_channels, but I am confused about how in_channel can be convert to out_channel,it there some method in low_sample? I am trying to read the code, but i got nothing. Can somboby has a different thought about that,it will help me a lot!!