The test loss changes strangely with learning rate 0?












0















I'm trying to study the performace of YOLOv2. I have implemented the YOLOv2 in tensorflow with the backbone of mobilenet.



After setting the learning rate=0, weight decay=0, BN's is_training=False, the loss of test dataset is still changing unexpectedly.



I just want to know if there is any other possible parameter may influence the test loss.










share|improve this question


















  • 1





    learning rate of zero sounds strange. try some small numbers like .0001

    – Ray Tayek
    Nov 20 '18 at 3:52











  • With the above setting, the whole network should be fixed and the loss should also be fixed. But results are not the way we expected. I'm trying to figure out what else influence the final loss.

    – Acroph
    Nov 20 '18 at 5:59
















0















I'm trying to study the performace of YOLOv2. I have implemented the YOLOv2 in tensorflow with the backbone of mobilenet.



After setting the learning rate=0, weight decay=0, BN's is_training=False, the loss of test dataset is still changing unexpectedly.



I just want to know if there is any other possible parameter may influence the test loss.










share|improve this question


















  • 1





    learning rate of zero sounds strange. try some small numbers like .0001

    – Ray Tayek
    Nov 20 '18 at 3:52











  • With the above setting, the whole network should be fixed and the loss should also be fixed. But results are not the way we expected. I'm trying to figure out what else influence the final loss.

    – Acroph
    Nov 20 '18 at 5:59














0












0








0








I'm trying to study the performace of YOLOv2. I have implemented the YOLOv2 in tensorflow with the backbone of mobilenet.



After setting the learning rate=0, weight decay=0, BN's is_training=False, the loss of test dataset is still changing unexpectedly.



I just want to know if there is any other possible parameter may influence the test loss.










share|improve this question














I'm trying to study the performace of YOLOv2. I have implemented the YOLOv2 in tensorflow with the backbone of mobilenet.



After setting the learning rate=0, weight decay=0, BN's is_training=False, the loss of test dataset is still changing unexpectedly.



I just want to know if there is any other possible parameter may influence the test loss.







tensorflow yolo






share|improve this question













share|improve this question











share|improve this question




share|improve this question










asked Nov 20 '18 at 3:47









AcrophAcroph

1




1








  • 1





    learning rate of zero sounds strange. try some small numbers like .0001

    – Ray Tayek
    Nov 20 '18 at 3:52











  • With the above setting, the whole network should be fixed and the loss should also be fixed. But results are not the way we expected. I'm trying to figure out what else influence the final loss.

    – Acroph
    Nov 20 '18 at 5:59














  • 1





    learning rate of zero sounds strange. try some small numbers like .0001

    – Ray Tayek
    Nov 20 '18 at 3:52











  • With the above setting, the whole network should be fixed and the loss should also be fixed. But results are not the way we expected. I'm trying to figure out what else influence the final loss.

    – Acroph
    Nov 20 '18 at 5:59








1




1





learning rate of zero sounds strange. try some small numbers like .0001

– Ray Tayek
Nov 20 '18 at 3:52





learning rate of zero sounds strange. try some small numbers like .0001

– Ray Tayek
Nov 20 '18 at 3:52













With the above setting, the whole network should be fixed and the loss should also be fixed. But results are not the way we expected. I'm trying to figure out what else influence the final loss.

– Acroph
Nov 20 '18 at 5:59





With the above setting, the whole network should be fixed and the loss should also be fixed. But results are not the way we expected. I'm trying to figure out what else influence the final loss.

– Acroph
Nov 20 '18 at 5:59












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
});


}
});














draft saved

draft discarded


















StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53385937%2fthe-test-loss-changes-strangely-with-learning-rate-0%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
















draft saved

draft discarded




















































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.




draft saved


draft discarded














StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53385937%2fthe-test-loss-changes-strangely-with-learning-rate-0%23new-answer', 'question_page');
}
);

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







Popular posts from this blog

android studio warns about leanback feature tag usage required on manifest while using Unity exported app?

SQL update select statement

'app-layout' is not a known element: how to share Component with different Modules