0
$\begingroup$

I found some confusion understanding the importance of vertical and horizontal stacks as a solution to the blind spot problem presented in the original pixel cnn architecture discussed in this paper. The vertical and horizontal stacks ideas were presented in the this paper.

Therefore, after browsing, I found this link to explain the concept. In the vertical stack section of the web page, I still find that pixel f, still cannot see pixels c, d and e.

Any help is much appreciated!!

| improve this question | | | | |
$\endgroup$
  • $\begingroup$ I don't think the paper is clearly written for people without experience with the old version of PixelCNN to understand the "horizontal" and "vertical" stacks... I feel I've wasted a day of my life for some irresponsible writing... $\endgroup$ – yuqli Feb 28 '19 at 2:52
0
$\begingroup$

I also had the same problem when reading the paper, I believe it is not explicitly mentioned. I think the whole image is padded with zeros on the top row when you are using the vertical stack. In this way, you ensure that the output of any pixel of row i will depend only on the pixels at row i-1 till row 0. But at the same time, you have the advantage of depth of field compositionality and remove the blind spot (given you are stacking enough convolutional layers).

| improve this answer | | | | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.