How to aggregate face embeddings of all photos of the same person?How to mitigate the hierarchical error propagation in tree-structured classificationSupport Vector Classification kernels ‘linear’, ‘poly’, ‘rbf’ has all same scoreHow can I know how to interpret the output coefficients (`coefs_`) from the model sklearn.svm.LinearSVC()?I trained my data and obtained a training score of 0.957. Why can't I get the data to provide a prediction even against the same training data?The effect of all zero value as the input of SVMHow to tune the hyper-parameters of an estimator in Orange ToolHow to quantify the performance of the classifier (multi-class SVM) using the test data?How do I interpret the length-scale parameter of the RBF kernel?Is the prediction algorithm absolutely the same for all linear classifiers?How to choose the support vectors after minimizing the objective function?
Is it idiomatic to construct against `this`
Function pointer with named arguments?
Critique of timeline aesthetic
Can SQL Server create collisions in system generated constraint names?
Why must Chinese maps be obfuscated?
Why do games have consumables?
How can Republicans who favour free markets, consistently express anger when they don't like the outcome of that choice?
Mistake in years of experience in resume?
Can someone publish a story that happened to you?
Which big number is bigger?
What is causing the white spot to appear in some of my pictures
What are the steps to solving this definite integral?
Don’t seats that recline flat defeat the purpose of having seatbelts?
Aliens crash on Earth and go into stasis to wait for technology to fix their ship
"The cow" OR "a cow" OR "cows" in this context
Contradiction proof for inequality of P and NP?
Dynamic SOQL query relationship with field visibility for Users
acheter à, to mean both "from" and "for"?
Is there really no use for MD5 anymore?
If a planet has 3 moons, is it possible to have triple Full/New Moons at once?
Is the claim "Employers won't employ people with no 'social media presence'" realistic?
How does Captain America channel this power?
Was there a shared-world project before "Thieves World"?
Rivers without rain
How to aggregate face embeddings of all photos of the same person?
How to mitigate the hierarchical error propagation in tree-structured classificationSupport Vector Classification kernels ‘linear’, ‘poly’, ‘rbf’ has all same scoreHow can I know how to interpret the output coefficients (`coefs_`) from the model sklearn.svm.LinearSVC()?I trained my data and obtained a training score of 0.957. Why can't I get the data to provide a prediction even against the same training data?The effect of all zero value as the input of SVMHow to tune the hyper-parameters of an estimator in Orange ToolHow to quantify the performance of the classifier (multi-class SVM) using the test data?How do I interpret the length-scale parameter of the RBF kernel?Is the prediction algorithm absolutely the same for all linear classifiers?How to choose the support vectors after minimizing the objective function?
$begingroup$
I am classifying about 3000 thousand people's faces using FaceNet. Each person has about 100 photos.
FaceNet first calculates a face embedding ( a feature vector) for each photo. So each person has 100 face embeddings.
What I want to do is aggregate the face embedding of each person into one. What is the best way of doing this?
I have tried to use mean method. But I am not sure whether this is recommended way.
--
The reason I want this is because using a single SVM as classifier for 3000 labels is very slow. (I took 50+ hours and about 250G memory and it still won't finish training). So I need to divide the training data into subsets, and use multiple SVCs to get first level of results. Then I uses the aggregated face-embedding of each person and closest distance to get second level result.
svm
asked Nov 26 '18 at 20:58
user8328365user8328365
62
$endgroup$
bumped to the homepage by Community♦ 48 secs 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 |
$begingroup$
I am classifying about 3000 thousand people's faces using FaceNet. Each person has about 100 photos.
FaceNet first calculates a face embedding ( a feature vector) for each photo. So each person has 100 face embeddings.
What I want to do is aggregate the face embedding of each person into one. What is the best way of doing this?
I have tried to use mean method. But I am not sure whether this is recommended way.
--
The reason I want this is because using a single SVM as classifier for 3000 labels is very slow. (I took 50+ hours and about 250G memory and it still won't finish training). So I need to divide the training data into subsets, and use multiple SVCs to get first level of results. Then I uses the aggregated face-embedding of each person and closest distance to get second level result.
svm
asked Nov 26 '18 at 20:58
user8328365user8328365
62
$endgroup$
bumped to the homepage by Community♦ 48 secs 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 |
$begingroup$
I am classifying about 3000 thousand people's faces using FaceNet. Each person has about 100 photos.
FaceNet first calculates a face embedding ( a feature vector) for each photo. So each person has 100 face embeddings.
What I want to do is aggregate the face embedding of each person into one. What is the best way of doing this?
I have tried to use mean method. But I am not sure whether this is recommended way.
--
The reason I want this is because using a single SVM as classifier for 3000 labels is very slow. (I took 50+ hours and about 250G memory and it still won't finish training). So I need to divide the training data into subsets, and use multiple SVCs to get first level of results. Then I uses the aggregated face-embedding of each person and closest distance to get second level result.
svm
asked Nov 26 '18 at 20:58
user8328365user8328365
62
$endgroup$
I am classifying about 3000 thousand people's faces using FaceNet. Each person has about 100 photos.
FaceNet first calculates a face embedding ( a feature vector) for each photo. So each person has 100 face embeddings.
What I want to do is aggregate the face embedding of each person into one. What is the best way of doing this?
I have tried to use mean method. But I am not sure whether this is recommended way.
--
The reason I want this is because using a single SVM as classifier for 3000 labels is very slow. (I took 50+ hours and about 250G memory and it still won't finish training). So I need to divide the training data into subsets, and use multiple SVCs to get first level of results. Then I uses the aggregated face-embedding of each person and closest distance to get second level result.
svm
svm
asked Nov 26 '18 at 20:58
user8328365user8328365
62
asked Nov 26 '18 at 20:58
user8328365user8328365
62
asked Nov 26 '18 at 20:58
user8328365user8328365
62
asked Nov 26 '18 at 20:58
user8328365user8328365
62
asked Nov 26 '18 at 20:58
user8328365user8328365
62
62
bumped to the homepage by Community♦ 48 secs ago
This question has answers that may be good or bad; the system has marked it active so that they can be reviewed.
bumped to the homepage by Community♦ 48 secs 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 |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
This question is the first I've heard of FaceNet, but I don't think that the right solution to the question is to aggregate the face embeddings but to ask why you're using an SVM to classify the embeddings. Importantly, many SVM implementations of multiclass classification use a one-vs-rest method to train the classifiers -- if you're using a one-vs-rest implementation with 3000 labels, I suspect that this is the reason your training is taking so long.
You should look into how your implementation is training the classifier. Additionally, How large is your embedding size?
answered Nov 27 '18 at 2:46
MatthewMatthew
57410
$endgroup$
$begingroup$
Thanks for the info. My intended application is face identification: given a face image, identify whose face it belongs out of 3000 people. I googled one-vs-all and one-vs-one classifier, it seems only one-vs-all classifier will fit this need. I guess the other implementation (one-vs-one) is for face authentication only? (check whehter the face is who it claim to be). My embedding size is 512.
$endgroup$
– user8328365
Nov 28 '18 at 6:30
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
);
);
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
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f41714%2fhow-to-aggregate-face-embeddings-of-all-photos-of-the-same-person%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
$begingroup$
This question is the first I've heard of FaceNet, but I don't think that the right solution to the question is to aggregate the face embeddings but to ask why you're using an SVM to classify the embeddings. Importantly, many SVM implementations of multiclass classification use a one-vs-rest method to train the classifiers -- if you're using a one-vs-rest implementation with 3000 labels, I suspect that this is the reason your training is taking so long.
You should look into how your implementation is training the classifier. Additionally, How large is your embedding size?
answered Nov 27 '18 at 2:46
MatthewMatthew
57410
$endgroup$
$begingroup$
Thanks for the info. My intended application is face identification: given a face image, identify whose face it belongs out of 3000 people. I googled one-vs-all and one-vs-one classifier, it seems only one-vs-all classifier will fit this need. I guess the other implementation (one-vs-one) is for face authentication only? (check whehter the face is who it claim to be). My embedding size is 512.
$endgroup$
– user8328365
Nov 28 '18 at 6:30
add a comment |
$begingroup$
This question is the first I've heard of FaceNet, but I don't think that the right solution to the question is to aggregate the face embeddings but to ask why you're using an SVM to classify the embeddings. Importantly, many SVM implementations of multiclass classification use a one-vs-rest method to train the classifiers -- if you're using a one-vs-rest implementation with 3000 labels, I suspect that this is the reason your training is taking so long.
You should look into how your implementation is training the classifier. Additionally, How large is your embedding size?
answered Nov 27 '18 at 2:46
MatthewMatthew
57410
$endgroup$
$begingroup$
Thanks for the info. My intended application is face identification: given a face image, identify whose face it belongs out of 3000 people. I googled one-vs-all and one-vs-one classifier, it seems only one-vs-all classifier will fit this need. I guess the other implementation (one-vs-one) is for face authentication only? (check whehter the face is who it claim to be). My embedding size is 512.
$endgroup$
– user8328365
Nov 28 '18 at 6:30
add a comment |
$begingroup$
This question is the first I've heard of FaceNet, but I don't think that the right solution to the question is to aggregate the face embeddings but to ask why you're using an SVM to classify the embeddings. Importantly, many SVM implementations of multiclass classification use a one-vs-rest method to train the classifiers -- if you're using a one-vs-rest implementation with 3000 labels, I suspect that this is the reason your training is taking so long.
You should look into how your implementation is training the classifier. Additionally, How large is your embedding size?
answered Nov 27 '18 at 2:46
MatthewMatthew
57410
$endgroup$
This question is the first I've heard of FaceNet, but I don't think that the right solution to the question is to aggregate the face embeddings but to ask why you're using an SVM to classify the embeddings. Importantly, many SVM implementations of multiclass classification use a one-vs-rest method to train the classifiers -- if you're using a one-vs-rest implementation with 3000 labels, I suspect that this is the reason your training is taking so long.
You should look into how your implementation is training the classifier. Additionally, How large is your embedding size?
answered Nov 27 '18 at 2:46
MatthewMatthew
57410
answered Nov 27 '18 at 2:46
MatthewMatthew
57410
answered Nov 27 '18 at 2:46
MatthewMatthew
57410
answered Nov 27 '18 at 2:46
MatthewMatthew
57410
57410
$begingroup$
Thanks for the info. My intended application is face identification: given a face image, identify whose face it belongs out of 3000 people. I googled one-vs-all and one-vs-one classifier, it seems only one-vs-all classifier will fit this need. I guess the other implementation (one-vs-one) is for face authentication only? (check whehter the face is who it claim to be). My embedding size is 512.
$endgroup$
– user8328365
Nov 28 '18 at 6:30
add a comment |
$begingroup$
Thanks for the info. My intended application is face identification: given a face image, identify whose face it belongs out of 3000 people. I googled one-vs-all and one-vs-one classifier, it seems only one-vs-all classifier will fit this need. I guess the other implementation (one-vs-one) is for face authentication only? (check whehter the face is who it claim to be). My embedding size is 512.
$endgroup$
– user8328365
Nov 28 '18 at 6:30
$begingroup$
Thanks for the info. My intended application is face identification: given a face image, identify whose face it belongs out of 3000 people. I googled one-vs-all and one-vs-one classifier, it seems only one-vs-all classifier will fit this need. I guess the other implementation (one-vs-one) is for face authentication only? (check whehter the face is who it claim to be). My embedding size is 512.
$endgroup$
– user8328365
Nov 28 '18 at 6:30
$begingroup$
Thanks for the info. My intended application is face identification: given a face image, identify whose face it belongs out of 3000 people. I googled one-vs-all and one-vs-one classifier, it seems only one-vs-all classifier will fit this need. I guess the other implementation (one-vs-one) is for face authentication only? (check whehter the face is who it claim to be). My embedding size is 512.
$endgroup$
– user8328365
Nov 28 '18 at 6:30
add a comment |
Thanks for contributing an answer to Data Science Stack Exchange!
- Please be sure to answer the question. Provide details and share your research!
But avoid …
- Asking for help, clarification, or responding to other answers.
- Making statements based on opinion; back them up with references or personal experience.
Use MathJax to format equations. MathJax reference.
To learn more, see our tips on writing great answers.
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
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f41714%2fhow-to-aggregate-face-embeddings-of-all-photos-of-the-same-person%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
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
Required, but never shown
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
Required, but never shown
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
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
