Trjtdtk

Is this toilet slogan correct usage of the English language?

Query about absorption line spectra

Loading commands from file

what is different between Do you interest vs interested in something?

Could the E-bike drivetrain wear down till needing replacement after 400 km?

Why is so much work done on numerical verification of the Riemann Hypothesis?

What should you do when eye contact makes your subordinate uncomfortable?

Travelling outside the UK without a passport

How do I nest cases?

What is this called? Old film camera viewer?

Customize circled numbers

Varistor? Purpose and principle

Is a model fitted to data or is data fitted to a model?

Count the occurrence of each unique word in the file

Why did the EU agree to delay the Brexit deadline?

Offered money to buy a house, seller is asking for more to cover gap between their listing and mortgage owed

Should I stop contributing to retirement accounts?

What should you do if you miss a job interview (deliberately)?

Why do we read the Megillah by night and by day?

Is there a name for this algorithm to calculate the concentration of a mixture of two solutions containing the same solute?

Which one is correct as adjective “protruding” or “protruded”?

Can I use Seifert-van Kampen theorem infinite times

Yosemite Fire Rings - What to Expect?

Why does the Sun have different day lengths, but not the gas giants?

Does Convolution kernel size affect number of channels?

how to propagate error from convolutional layer to previous layer？TensorFlow: number of channels of conv1d filtertuning a convolution neural net, sample sizeProof of Kernel PropertyHow does convolution operation perform in CNN?Why convolution over volume sums up across channels?What advantage does Guassian kernel have than any other kernels, such as linear kernel, polynomial kernel and so on?What is the purpose of a 1x1 convolutional layer?degeneracy of a CNN having only 1 convolution kernel down to a fully connected NNHow to choose the number of output channels in a convolutional layer?

0

$begingroup$

I am going through Dilated Residual Network blog post. In this, Under 2.Multi-scale Context aggregation heading, author mentioned this.

The last one is the 1×1 convolutions for mapping the number of
channels to be the same as the input one. Therefore, the input and the
output has the same number of channels. And it can be inserted to
different kinds of convolutional neural networks.

I thought, we decide number of channels in the next layer and kernels will be initialized randomly. These kernels shape is decided by us which are 1x1 or 3x3 etc., So, what did author mean when he said, 1x1 convolutions for mapping the number of channels to be the same as the input one.When, Even if its 2x2 convolutional kernel, number of channels are not changed.

deep-learning cnn kernel

share|improve this question

asked Mar 20 at 12:00

InAFlashInAFlash

3521315

$endgroup$

add a comment | 

0

$begingroup$

I am going through Dilated Residual Network blog post. In this, Under 2.Multi-scale Context aggregation heading, author mentioned this.

The last one is the 1×1 convolutions for mapping the number of
channels to be the same as the input one. Therefore, the input and the
output has the same number of channels. And it can be inserted to
different kinds of convolutional neural networks.

I thought, we decide number of channels in the next layer and kernels will be initialized randomly. These kernels shape is decided by us which are 1x1 or 3x3 etc., So, what did author mean when he said, 1x1 convolutions for mapping the number of channels to be the same as the input one.When, Even if its 2x2 convolutional kernel, number of channels are not changed.

deep-learning cnn kernel

share|improve this question

asked Mar 20 at 12:00

InAFlashInAFlash

3521315

$endgroup$

add a comment | 

$begingroup$

I am going through Dilated Residual Network blog post. In this, Under 2.Multi-scale Context aggregation heading, author mentioned this.

The last one is the 1×1 convolutions for mapping the number of
channels to be the same as the input one. Therefore, the input and the
output has the same number of channels. And it can be inserted to
different kinds of convolutional neural networks.

I thought, we decide number of channels in the next layer and kernels will be initialized randomly. These kernels shape is decided by us which are 1x1 or 3x3 etc., So, what did author mean when he said, 1x1 convolutions for mapping the number of channels to be the same as the input one.When, Even if its 2x2 convolutional kernel, number of channels are not changed.

deep-learning cnn kernel

share|improve this question

asked Mar 20 at 12:00

InAFlashInAFlash

3521315

$endgroup$

share|improve this question

asked Mar 20 at 12:00

InAFlashInAFlash

3521315

share|improve this question

asked Mar 20 at 12:00

InAFlashInAFlash

3521315

asked Mar 20 at 12:00

InAFlashInAFlash

3521315

asked Mar 20 at 12:00

InAFlashInAFlash

3521315

1 Answer
1

active

oldest

votes

0

$begingroup$

Normally a convolutional neural network will get flattened into a single column vector after the convolutions and then maybe be processed by dense layer. In this model, the convolution $1times1$ is used as an output layer. It will have $C$ channels like every other layer, but it is not dilatated. Hence, you can use this layer as the input to other convolutional neural networks.

The kernel size will not influence the channels. Imagine an RGB image with 4 by 4 pixels. If we have a $2times 2$ convolution with $2times 2$ stride we will get an output of dimension $3times 2 times 2$ (without padding). Hence the channels do not change. If we have $K$ filters we will ket $K$ times a $3times 2 times 2$ output. If the kernel size is $4times 4$ with a stride of $2times 2$ we will get a $3times 1 times 1$ (without padding) output for each of the $K$ filters. The kernel size only influences how large the receptive field of the convolutions are. Hence, it only influences how the layer is scaling the individual dimensions of the width and height (by using RGB images as an example).

If you flatten the output of a layer you will always reduce its dimensionality to $1$. In the dilated convolutional neural network they do not have a layer that flattens the input.

share|improve this answer

edited Mar 20 at 12:51

answered Mar 20 at 12:18

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  i think, it does not have 3 channels. Number of channels are increased if you actually see.It increased till last layer and Its C in last layers. Am i wrong?
  $endgroup$
  – InAFlash
  Mar 20 at 12:21
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @InAFlash: For the basic network the layer always stays at $C$ channels. I assumed RGB images, hence $C=3$. I corrected this. You could also take any other layer of the basic network and feed it into another network.
  $endgroup$
  – MachineLearner
  Mar 20 at 12:24
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  if you see, for large network, its not. And my question was how kernel size is related to number of channels.Thanks
  $endgroup$
  – InAFlash
  Mar 20 at 12:27
  

  
  
  
  


• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  @InAFlash I reached the same conclusion. Kernel 1x1 can give C channels, 2C channels, any channels. Just like kernel 3x3, which can give C channels, 32C channels, any channels. So the statement "1x1 because the same channels" seems unjustified in the article.
  $endgroup$
  – Esmailian
  Mar 20 at 12:44
  
  

  
  
  
  


• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  @InAFlash: The author just wants to emphasize that the last layer is not flattened to ensure that the output can be used for other networks. The author could have been more precise in explaining his/her point.
  $endgroup$
  – MachineLearner
  Mar 20 at 12:46
  

  
  
  
  

 | 
show 3 more comments

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%2f47665%2fdoes-convolution-kernel-size-affect-number-of-channels%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

0

$begingroup$

Normally a convolutional neural network will get flattened into a single column vector after the convolutions and then maybe be processed by dense layer. In this model, the convolution $1times1$ is used as an output layer. It will have $C$ channels like every other layer, but it is not dilatated. Hence, you can use this layer as the input to other convolutional neural networks.

The kernel size will not influence the channels. Imagine an RGB image with 4 by 4 pixels. If we have a $2times 2$ convolution with $2times 2$ stride we will get an output of dimension $3times 2 times 2$ (without padding). Hence the channels do not change. If we have $K$ filters we will ket $K$ times a $3times 2 times 2$ output. If the kernel size is $4times 4$ with a stride of $2times 2$ we will get a $3times 1 times 1$ (without padding) output for each of the $K$ filters. The kernel size only influences how large the receptive field of the convolutions are. Hence, it only influences how the layer is scaling the individual dimensions of the width and height (by using RGB images as an example).

If you flatten the output of a layer you will always reduce its dimensionality to $1$. In the dilated convolutional neural network they do not have a layer that flattens the input.

share|improve this answer

edited Mar 20 at 12:51

answered Mar 20 at 12:18

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  i think, it does not have 3 channels. Number of channels are increased if you actually see.It increased till last layer and Its C in last layers. Am i wrong?
  $endgroup$
  – InAFlash
  Mar 20 at 12:21
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @InAFlash: For the basic network the layer always stays at $C$ channels. I assumed RGB images, hence $C=3$. I corrected this. You could also take any other layer of the basic network and feed it into another network.
  $endgroup$
  – MachineLearner
  Mar 20 at 12:24
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  if you see, for large network, its not. And my question was how kernel size is related to number of channels.Thanks
  $endgroup$
  – InAFlash
  Mar 20 at 12:27
  

  
  
  
  


• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  @InAFlash I reached the same conclusion. Kernel 1x1 can give C channels, 2C channels, any channels. Just like kernel 3x3, which can give C channels, 32C channels, any channels. So the statement "1x1 because the same channels" seems unjustified in the article.
  $endgroup$
  – Esmailian
  Mar 20 at 12:44
  
  

  
  
  
  


• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  @InAFlash: The author just wants to emphasize that the last layer is not flattened to ensure that the output can be used for other networks. The author could have been more precise in explaining his/her point.
  $endgroup$
  – MachineLearner
  Mar 20 at 12:46
  

  
  
  
  

 | 
show 3 more comments

0

$begingroup$

Normally a convolutional neural network will get flattened into a single column vector after the convolutions and then maybe be processed by dense layer. In this model, the convolution $1times1$ is used as an output layer. It will have $C$ channels like every other layer, but it is not dilatated. Hence, you can use this layer as the input to other convolutional neural networks.

The kernel size will not influence the channels. Imagine an RGB image with 4 by 4 pixels. If we have a $2times 2$ convolution with $2times 2$ stride we will get an output of dimension $3times 2 times 2$ (without padding). Hence the channels do not change. If we have $K$ filters we will ket $K$ times a $3times 2 times 2$ output. If the kernel size is $4times 4$ with a stride of $2times 2$ we will get a $3times 1 times 1$ (without padding) output for each of the $K$ filters. The kernel size only influences how large the receptive field of the convolutions are. Hence, it only influences how the layer is scaling the individual dimensions of the width and height (by using RGB images as an example).

If you flatten the output of a layer you will always reduce its dimensionality to $1$. In the dilated convolutional neural network they do not have a layer that flattens the input.

share|improve this answer

edited Mar 20 at 12:51

answered Mar 20 at 12:18

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  i think, it does not have 3 channels. Number of channels are increased if you actually see.It increased till last layer and Its C in last layers. Am i wrong?
  $endgroup$
  – InAFlash
  Mar 20 at 12:21
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  @InAFlash: For the basic network the layer always stays at $C$ channels. I assumed RGB images, hence $C=3$. I corrected this. You could also take any other layer of the basic network and feed it into another network.
  $endgroup$
  – MachineLearner
  Mar 20 at 12:24
  
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  if you see, for large network, its not. And my question was how kernel size is related to number of channels.Thanks
  $endgroup$
  – InAFlash
  Mar 20 at 12:27
  

  
  
  
  


• 
  
  
  

  
  1
  

  
  
  
  
  
  

  
  $begingroup$
  @InAFlash I reached the same conclusion. Kernel 1x1 can give C channels, 2C channels, any channels. Just like kernel 3x3, which can give C channels, 32C channels, any channels. So the statement "1x1 because the same channels" seems unjustified in the article.
  $endgroup$
  – Esmailian
  Mar 20 at 12:44
  
  

  
  
  
  


• 
  
  
  

  
  2
  

  
  
  
  
  
  

  
  $begingroup$
  @InAFlash: The author just wants to emphasize that the last layer is not flattened to ensure that the output can be used for other networks. The author could have been more precise in explaining his/her point.
  $endgroup$
  – MachineLearner
  Mar 20 at 12:46
  

  
  
  
  

 | 
show 3 more comments

$begingroup$

Normally a convolutional neural network will get flattened into a single column vector after the convolutions and then maybe be processed by dense layer. In this model, the convolution $1times1$ is used as an output layer. It will have $C$ channels like every other layer, but it is not dilatated. Hence, you can use this layer as the input to other convolutional neural networks.

The kernel size will not influence the channels. Imagine an RGB image with 4 by 4 pixels. If we have a $2times 2$ convolution with $2times 2$ stride we will get an output of dimension $3times 2 times 2$ (without padding). Hence the channels do not change. If we have $K$ filters we will ket $K$ times a $3times 2 times 2$ output. If the kernel size is $4times 4$ with a stride of $2times 2$ we will get a $3times 1 times 1$ (without padding) output for each of the $K$ filters. The kernel size only influences how large the receptive field of the convolutions are. Hence, it only influences how the layer is scaling the individual dimensions of the width and height (by using RGB images as an example).

If you flatten the output of a layer you will always reduce its dimensionality to $1$. In the dilated convolutional neural network they do not have a layer that flattens the input.

share|improve this answer

edited Mar 20 at 12:51

answered Mar 20 at 12:18

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

share|improve this answer

edited Mar 20 at 12:51

answered Mar 20 at 12:18

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

answered Mar 20 at 12:18

MachineLearnerMachineLearner

32410

New contributor

MachineLearner is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

answered Mar 20 at 12:18

MachineLearnerMachineLearner

32410