Hfrxdjt

Why is there so little support for joining EFTA in the British parliament?

What does 丫 mean? 丫是什么意思？

In musical terms, what properties are varied by the human voice to produce different words / syllables?

What criticisms of Wittgenstein's philosophy of language have been offered?

newbie Q : How to read an output file in one command line

How does the body cool itself in a stillsuit?

How to make an animal which can only breed for a certain number of generations?

How could a hydrazine and N2O4 cloud (or it's reactants) show up in weather radar?

How to achieve cat-like agility?

latest version of QGIS fails to edit attribute table of GeoJSON file

Noise in Eigenvalues plot

Found this skink in my tomato plant bucket. Is he trapped? Or could he leave if he wanted?

Is this Kuo-toa homebrew race balanced?

Where did Ptolemy compare the Earth to the distance of fixed stars?

Is this Half-dragon Quaggoth boss monster balanced?

Why did Bronn offer to be Tyrion Lannister's champion in trial by combat?

Is a copyright notice with a non-existent name be invalid?

One-one communication

Keep at all times, the minus sign above aligned with minus sign below

NIntegrate on a solution of a matrix ODE

Do i imagine the linear (straight line) homotopy in a correct way?

Are there any irrational/transcendental numbers for which the distribution of decimal digits is not uniform?

What did Turing mean when saying that "machines cannot give rise to surprises" is due to a fallacy?

Why are two-digit numbers in Jonathan Swift's "Gulliver's Travels" (1726) written in "German style"?

Accessing and Multiplying Individual Elements of a Layer's Output in Keras

0

$begingroup$

Problem Description:

I am trying to access the individual elements (i.e., scalar) from a softmax layer's output (with dimension (,2)) and multiply this with a tensor from another model, which has a dimension of (,10). A mock-up digram describing my problem is shown in the attached Figure.

I am using Keras with Tensorflow as the back-end. So far, my approach has been the following: Lets say the output dimension of the softmax layer is (,2) (i.e., a vector of size 2). First, my plan is to access the individual elements of this vector (tensor according to the Keras/tensorflow) using the keras.backend.gather(a_k_p,0). Where, the variable a_k_p references the SoftmaxLayer.
However, gather simply gives the entire row and does not give the individual element. So, my first question is how to access individual elements of a layer's output?

Assuming I get an answer to the above question, I am describing my idea to multiply a scalar with a tensor as follows. First, replicate this scalar element to create a vector (i.e., a tensor) of size that matches with the DenseLayerA and DenseLayerB (in this case (,10)) and perform the multiplication. Now, I am not sure if this is the right approach since I am unsuccessful in retrieving the individual elements of the Sofmax Layer's output. So, is my approach correct? if not, what is the right way to solve my problem.

python deep-learning keras tensorflow

share|improve this question

asked Jul 22 '18 at 0:12

RkzRkz

3881312

$endgroup$

bumped to the homepage by Community♦ 3 hours ago

This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.

add a comment | 

0

$begingroup$

Problem Description:

I am trying to access the individual elements (i.e., scalar) from a softmax layer's output (with dimension (,2)) and multiply this with a tensor from another model, which has a dimension of (,10). A mock-up digram describing my problem is shown in the attached Figure.

I am using Keras with Tensorflow as the back-end. So far, my approach has been the following: Lets say the output dimension of the softmax layer is (,2) (i.e., a vector of size 2). First, my plan is to access the individual elements of this vector (tensor according to the Keras/tensorflow) using the keras.backend.gather(a_k_p,0). Where, the variable a_k_p references the SoftmaxLayer.
However, gather simply gives the entire row and does not give the individual element. So, my first question is how to access individual elements of a layer's output?

Assuming I get an answer to the above question, I am describing my idea to multiply a scalar with a tensor as follows. First, replicate this scalar element to create a vector (i.e., a tensor) of size that matches with the DenseLayerA and DenseLayerB (in this case (,10)) and perform the multiplication. Now, I am not sure if this is the right approach since I am unsuccessful in retrieving the individual elements of the Sofmax Layer's output. So, is my approach correct? if not, what is the right way to solve my problem.

python deep-learning keras tensorflow

share|improve this question

asked Jul 22 '18 at 0:12

RkzRkz

3881312

$endgroup$

bumped to the homepage by Community♦ 3 hours ago

This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.

add a comment | 

$begingroup$

Problem Description:

I am trying to access the individual elements (i.e., scalar) from a softmax layer's output (with dimension (,2)) and multiply this with a tensor from another model, which has a dimension of (,10). A mock-up digram describing my problem is shown in the attached Figure.

I am using Keras with Tensorflow as the back-end. So far, my approach has been the following: Lets say the output dimension of the softmax layer is (,2) (i.e., a vector of size 2). First, my plan is to access the individual elements of this vector (tensor according to the Keras/tensorflow) using the keras.backend.gather(a_k_p,0). Where, the variable a_k_p references the SoftmaxLayer.
However, gather simply gives the entire row and does not give the individual element. So, my first question is how to access individual elements of a layer's output?

Assuming I get an answer to the above question, I am describing my idea to multiply a scalar with a tensor as follows. First, replicate this scalar element to create a vector (i.e., a tensor) of size that matches with the DenseLayerA and DenseLayerB (in this case (,10)) and perform the multiplication. Now, I am not sure if this is the right approach since I am unsuccessful in retrieving the individual elements of the Sofmax Layer's output. So, is my approach correct? if not, what is the right way to solve my problem.

python deep-learning keras tensorflow

share|improve this question

asked Jul 22 '18 at 0:12

RkzRkz

3881312

$endgroup$

share|improve this question

asked Jul 22 '18 at 0:12

RkzRkz

3881312

share|improve this question

asked Jul 22 '18 at 0:12

RkzRkz

3881312

asked Jul 22 '18 at 0:12

RkzRkz

3881312

asked Jul 22 '18 at 0:12

RkzRkz

3881312

1 Answer
1

active

oldest

votes

0

$begingroup$

This line of code will select the highest value in your softmax function. If you'd like more than one value just change the 1 to whichever value you'd like. I hope this helps.

top_value = tf.nn.in_top_k(logits, y, 1)

share|improve this answer

answered Jul 23 '18 at 3:19

stephen barterstephen barter

293

$endgroup$

add a comment | 

Your Answer

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%2f35851%2faccessing-and-multiplying-individual-elements-of-a-layers-output-in-keras%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

0

$begingroup$

This line of code will select the highest value in your softmax function. If you'd like more than one value just change the 1 to whichever value you'd like. I hope this helps.

top_value = tf.nn.in_top_k(logits, y, 1)

share|improve this answer

answered Jul 23 '18 at 3:19

stephen barterstephen barter

293

$endgroup$

add a comment | 

0

$begingroup$

This line of code will select the highest value in your softmax function. If you'd like more than one value just change the 1 to whichever value you'd like. I hope this helps.

top_value = tf.nn.in_top_k(logits, y, 1)

share|improve this answer

answered Jul 23 '18 at 3:19

stephen barterstephen barter

293

$endgroup$

add a comment | 

$begingroup$

This line of code will select the highest value in your softmax function. If you'd like more than one value just change the 1 to whichever value you'd like. I hope this helps.

top_value = tf.nn.in_top_k(logits, y, 1)

share|improve this answer

answered Jul 23 '18 at 3:19

stephen barterstephen barter

293

$endgroup$

top_value = tf.nn.in_top_k(logits, y, 1)

share|improve this answer

answered Jul 23 '18 at 3:19

stephen barterstephen barter

293

answered Jul 23 '18 at 3:19

stephen barterstephen barter

293

answered Jul 23 '18 at 3:19

stephen barterstephen barter

293