Ggthjy

How can a school be getting an epidemic of whooping cough if most of the students are vaccinated?

Use two 8s and two 3s to make the number 24

How do you funnel food off a cutting board?

Why zero tolerance on nudity in space?

Why exactly do action photographers need high fps burst cameras?

Why avoid shared user accounts?

Is using an 'empty' metaphor considered bad style?

What is a good reason for every spaceship to carry a weapon on board?

Is a new Boolean field better than a null reference when a value can be meaningfully absent?

A starship is travelling at 0.9c and collides with a small rock. Will it leave a clean hole through, or will more happen?

Increment each digit in a number to form a new number

Has any human ever had the choice to leave Earth permanently?

Mathematics and the art of linearizing the circle

Quickly creating a sparse array

What evolutionary advantage do viruses have in host specificity?

Finding a logistic regression model which can achieve zero error on a training set training data for a binary classification problem with two features

Why was Lupin comfortable with saying Voldemort's name?

How can my powered armor quickly replace its ceramic plates?

Removing disk while game is suspended

Why don't hotels mount air conditioning units outside the rooms?

What are "industrial chops"?

Is it possible to grant users sftp access without shell access? If yes, how is it implemented?

Difference between i++ and (i)++ in C

What incentives do banks have to gather up loans into pools (backed by Ginnie Mae)and selling them?

Understanding The Vertical and Horizontal stack in conditional gated Pixelcnn paper

Understanding dropout and gradient descentBest machine learning algorithm for understanding specific conditional structuresTraining a Detection Network on a tricky datasetUnderstanding regularisation and a preference for small weightsUnderstanding cnnunderstanding the filter function in convolution neural networkCustom conditional Keras metricUnderstanding Embeddings input and output sizesUnderstanding YOLO Loss FunctionRecognizing circled numbers on a piece of paper

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!!

neural-network cnn

share|improve this question

edited Feb 19 at 17:42

ebrahimi

73121021

asked Aug 29 '18 at 15:20

I. AI. A

13717

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  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
  3 mins ago
  

  
  
  
  

add a comment | 

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!!

neural-network cnn

share|improve this question

edited Feb 19 at 17:42

ebrahimi

73121021

asked Aug 29 '18 at 15:20

I. AI. A

13717

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  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
  3 mins ago
  

  
  
  
  

add a comment | 

$begingroup$

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!!

neural-network cnn

share|improve this question

edited Feb 19 at 17:42

ebrahimi

73121021

asked Aug 29 '18 at 15:20

I. AI. A

13717

$endgroup$

share|improve this question

edited Feb 19 at 17:42

ebrahimi

73121021

asked Aug 29 '18 at 15:20

I. AI. A

13717

share|improve this question

edited Feb 19 at 17:42

ebrahimi

73121021

asked Aug 29 '18 at 15:20

I. AI. A

13717

edited Feb 19 at 17:42

ebrahimi

73121021

edited Feb 19 at 17:42

ebrahimi

73121021

asked Aug 29 '18 at 15:20

I. AI. A

13717

asked Aug 29 '18 at 15:20

I. AI. A

13717

1 Answer
1

active

oldest

votes

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).

share|improve this answer

edited Feb 19 at 22:30

answered Feb 19 at 9:21

ricvoricvo

11

$endgroup$

add a comment | 

Your Answer

StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "557"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});

function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});


}
});

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Sign up using Google

Sign up using Facebook

Sign up using Email and Password

Post as a guest

Name

Email

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f37569%2funderstanding-the-vertical-and-horizontal-stack-in-conditional-gated-pixelcnn-pa%23new-answer', 'question_page');
}
);

Post as a guest

Name

Email

Required, but never shown

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).

share|improve this answer

edited Feb 19 at 22:30

answered Feb 19 at 9:21

ricvoricvo

11

$endgroup$

add a comment | 

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).

share|improve this answer

edited Feb 19 at 22:30

answered Feb 19 at 9:21

ricvoricvo

11

$endgroup$

add a comment | 

$begingroup$

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).

share|improve this answer

edited Feb 19 at 22:30

answered Feb 19 at 9:21

ricvoricvo

11

$endgroup$

share|improve this answer

edited Feb 19 at 22:30

answered Feb 19 at 9:21

ricvoricvo

11

answered Feb 19 at 9:21

ricvoricvo

11

answered Feb 19 at 9:21

ricvoricvo

11