multilabel classification implement
I want to perform multilabel classification (attribute prediction for celeba images). I want to use the tf.losses.sigmoid_cross_entropy function.
Is it correct to give the correct answer labels as multi_class_labels(parameter) and the result of passing the last fc layer of CNN (which spits the size of the correct label) as logits(parameter)?
It seems that various sources are implemented as such, but I thought that it will be correct to give the result of passing batch_normalization + sigmoid after the last fc layer as logits(parameter) to get the right performance. And it seems to actually produce the right performance.
The attribute data has 25 labels, almost all of 0, and sex and is_young have 1 more (total 0 is 84%). In the former implementation, 93% shows accuracy and the latter shows 99% accuracy. But I'm not sure if the latter is the right implementation.
Can I use it like this?
(And moreover Is it difficult to learn if 1 is more than 0 in the data?)
python tensorflow
edited Nov 26 '18 at 10:59
Dave
2,24651625
asked Nov 26 '18 at 1:33
김영국김영국
11
add a comment |
I want to perform multilabel classification (attribute prediction for celeba images). I want to use the tf.losses.sigmoid_cross_entropy function.
Is it correct to give the correct answer labels as multi_class_labels(parameter) and the result of passing the last fc layer of CNN (which spits the size of the correct label) as logits(parameter)?
It seems that various sources are implemented as such, but I thought that it will be correct to give the result of passing batch_normalization + sigmoid after the last fc layer as logits(parameter) to get the right performance. And it seems to actually produce the right performance.
The attribute data has 25 labels, almost all of 0, and sex and is_young have 1 more (total 0 is 84%). In the former implementation, 93% shows accuracy and the latter shows 99% accuracy. But I'm not sure if the latter is the right implementation.
Can I use it like this?
(And moreover Is it difficult to learn if 1 is more than 0 in the data?)
python tensorflow
edited Nov 26 '18 at 10:59
Dave
2,24651625
asked Nov 26 '18 at 1:33
김영국김영국
11
add a comment |
I want to perform multilabel classification (attribute prediction for celeba images). I want to use the tf.losses.sigmoid_cross_entropy function.
Is it correct to give the correct answer labels as multi_class_labels(parameter) and the result of passing the last fc layer of CNN (which spits the size of the correct label) as logits(parameter)?
It seems that various sources are implemented as such, but I thought that it will be correct to give the result of passing batch_normalization + sigmoid after the last fc layer as logits(parameter) to get the right performance. And it seems to actually produce the right performance.
The attribute data has 25 labels, almost all of 0, and sex and is_young have 1 more (total 0 is 84%). In the former implementation, 93% shows accuracy and the latter shows 99% accuracy. But I'm not sure if the latter is the right implementation.
Can I use it like this?
(And moreover Is it difficult to learn if 1 is more than 0 in the data?)
python tensorflow
edited Nov 26 '18 at 10:59
Dave
2,24651625
asked Nov 26 '18 at 1:33
김영국김영국
11
I want to perform multilabel classification (attribute prediction for celeba images). I want to use the tf.losses.sigmoid_cross_entropy function.
Is it correct to give the correct answer labels as multi_class_labels(parameter) and the result of passing the last fc layer of CNN (which spits the size of the correct label) as logits(parameter)?
It seems that various sources are implemented as such, but I thought that it will be correct to give the result of passing batch_normalization + sigmoid after the last fc layer as logits(parameter) to get the right performance. And it seems to actually produce the right performance.
The attribute data has 25 labels, almost all of 0, and sex and is_young have 1 more (total 0 is 84%). In the former implementation, 93% shows accuracy and the latter shows 99% accuracy. But I'm not sure if the latter is the right implementation.
Can I use it like this?
(And moreover Is it difficult to learn if 1 is more than 0 in the data?)
python tensorflow
python tensorflow
edited Nov 26 '18 at 10:59
Dave
2,24651625
asked Nov 26 '18 at 1:33
김영국김영국
11
edited Nov 26 '18 at 10:59
Dave
2,24651625
asked Nov 26 '18 at 1:33
김영국김영국
11
edited Nov 26 '18 at 10:59
Dave
2,24651625
edited Nov 26 '18 at 10:59
Dave
2,24651625
edited Nov 26 '18 at 10:59
Dave
2,24651625
2,24651625
asked Nov 26 '18 at 1:33
김영국김영국
11
asked Nov 26 '18 at 1:33
김영국김영국
11
asked Nov 26 '18 at 1:33
김영국김영국
11
11
add a comment |
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");
StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
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: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
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%2fstackoverflow.com%2fquestions%2f53473727%2fmultilabel-classification-implement%23new-answer', 'question_page');
}
);
Post as a guest
Required, but never shown
0
active
oldest
votes
0
active
oldest
votes
active
oldest
votes
active
oldest
votes
Thanks for contributing an answer to Stack Overflow!
- 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.
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%2fstackoverflow.com%2fquestions%2f53473727%2fmultilabel-classification-implement%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
