Why loss and val_loss vary for same value of lr, epoch, batch size and lr-decay?
$begingroup$
I am training a deep neural network in Keras. I have set the values of learning rate, learning rate decay, epochs and batch size.
(I am using fit_generator i.e data coming from a generator but without any kind of shuffling.)
Being said that my training shows highly differenttraining summary.
Sometimes it's like:
And other times it is
The two of the above images show the highly unpredictable behavior of model for the same values of all hyperparameters.
Can someone explain why this is happening?
keras predictive-modeling
asked 23 hours ago
yamini goelyamini goel
214
$endgroup$
add a comment |
$begingroup$
I am training a deep neural network in Keras. I have set the values of learning rate, learning rate decay, epochs and batch size.
(I am using fit_generator i.e data coming from a generator but without any kind of shuffling.)
Being said that my training shows highly differenttraining summary.
Sometimes it's like:
And other times it is
The two of the above images show the highly unpredictable behavior of model for the same values of all hyperparameters.
Can someone explain why this is happening?
keras predictive-modeling
asked 23 hours ago
yamini goelyamini goel
214
$endgroup$
1
$begingroup$
The changes do look a bit extreme. Can your add more details about the task your model suppose to do and the characteristics of the datasets you are using?
$endgroup$
– Mark.F
18 hours ago
add a comment |
$begingroup$
I am training a deep neural network in Keras. I have set the values of learning rate, learning rate decay, epochs and batch size.
(I am using fit_generator i.e data coming from a generator but without any kind of shuffling.)
Being said that my training shows highly differenttraining summary.
Sometimes it's like:
And other times it is
The two of the above images show the highly unpredictable behavior of model for the same values of all hyperparameters.
Can someone explain why this is happening?
keras predictive-modeling
asked 23 hours ago
yamini goelyamini goel
214
$endgroup$
I am training a deep neural network in Keras. I have set the values of learning rate, learning rate decay, epochs and batch size.
(I am using fit_generator i.e data coming from a generator but without any kind of shuffling.)
Being said that my training shows highly differenttraining summary.
Sometimes it's like:
And other times it is
The two of the above images show the highly unpredictable behavior of model for the same values of all hyperparameters.
Can someone explain why this is happening?
keras predictive-modeling
keras predictive-modeling
asked 23 hours ago
yamini goelyamini goel
214
asked 23 hours ago
yamini goelyamini goel
214
edited 22 hours ago
yamini goel
asked 23 hours ago
yamini goelyamini goel
214
asked 23 hours ago
yamini goelyamini goel
214
asked 23 hours ago
yamini goelyamini goel
214
214
1
$begingroup$
The changes do look a bit extreme. Can your add more details about the task your model suppose to do and the characteristics of the datasets you are using?
$endgroup$
– Mark.F
18 hours ago
add a comment |
1
$begingroup$
The changes do look a bit extreme. Can your add more details about the task your model suppose to do and the characteristics of the datasets you are using?
$endgroup$
– Mark.F
18 hours ago
1
1
$begingroup$
The changes do look a bit extreme. Can your add more details about the task your model suppose to do and the characteristics of the datasets you are using?
$endgroup$
– Mark.F
18 hours ago
$begingroup$
The changes do look a bit extreme. Can your add more details about the task your model suppose to do and the characteristics of the datasets you are using?
$endgroup$
– Mark.F
18 hours ago
add a comment |
0
active
oldest
votes
Your Answer
StackExchange.ifUsing("editor", function () {
return StackExchange.using("mathjaxEditing", function () {
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
});
});
}, "mathjax-editing");
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%2f47648%2fwhy-loss-and-val-loss-vary-for-same-value-of-lr-epoch-batch-size-and-lr-decay%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 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%2f47648%2fwhy-loss-and-val-loss-vary-for-same-value-of-lr-epoch-batch-size-and-lr-decay%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
$begingroup$
The changes do look a bit extreme. Can your add more details about the task your model suppose to do and the characteristics of the datasets you are using?
$endgroup$
– Mark.F
18 hours ago