The test loss changes strangely with learning rate 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.
tensorflow yolo
add a comment |
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
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
add a comment |
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
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
tensorflow yolo
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
add a comment |
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
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%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
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%2f53385937%2fthe-test-loss-changes-strangely-with-learning-rate-0%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
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