Possibly a mistake?

[alex-golts]

Shouldn't this line https://github.com/1zb/pytorch-image-comp-rnn/blob/980f2ff6733c37ca0f4ecce9685a78fd873b2b3c/train.py#L155

be res = res0 - output, where res0 = patches - 0.5?

Rather than res = res - output ?

The residual at each iteration should be with respect to the original image, no?

[1zb]

I think what you are talking about is one-shot reconstruction which is mentioned in section 2.2 of this paper.

[alex-golts]

@1zb I get it now, thanks!