Keras: extreme spike in loss during trainingKeras difference beetween val_loss and loss during trainingThe...
Digits in an algebraic irrational number
Using only 1s, make 29 with the minimum number of digits
How can my powered armor quickly replace its ceramic plates?
Caruana vs Carlsen game 10 (WCC) why not 18...Nxb6?
Roman Numerals equation 1
Strange Sign on Lab Door
Word or phrase for showing great skill at something WITHOUT formal training in it
Traveling through the asteriod belt?
How to solve a large system of linear algebra?
Injecting creativity into a cookbook
How much mayhem could I cause as a sentient fish?
Am I a Rude Number?
How can I get my players to come to the game session after agreeing to a date?
Why are the books in the Game of Thrones citadel library shelved spine inwards?
How long is the D&D Starter Set campaign?
Is that a center tap tranformer just labelled differently?
My cat mixes up the floors in my building. How can I help him?
How to count the characters of jar files by wc
awk + sum all numbers
What is the purpose of easy combat scenarios that don't need resource expenditure?
Dilemma of explaining to interviewer that he is the reason for declining second interview
How to deal with an incendiary email that was recalled
Blindfold battle as a gladiatorial spectacle - what are the tactics and communication methods?
Cookies - Should the toggles be on?
Keras: extreme spike in loss during training
Keras difference beetween val_loss and loss during trainingThe validation loss < training loss and validation accuracy < training accuracySimple prediction with KerasHow to set input for proper fit with lstm?My Neural network in Tensorflow does a bad job in comparison to the same Neural network in KerasWhy is predicted rainfall by LSTM coming negative for some data points?Triplet loss training problemImages Score Regression only regresses to the average of the target valuesWhy doesn't loss go down during Neural Net training?keras plotting loss and MSE
$begingroup$
I am training an LSTM for time series forecasting and it has produced an extremly high loss value during one epoch:
Epoch 00043: saving model to /...
904/904 - 2s - loss: 0.7537 - mean_absolute_error: 0.5772 - val_loss: 1.4430
- val_mean_absolute_error: 0.7124
Epoch 00044: saving model to /...
904/904 - 2s - loss: 240372339275.7649 - mean_absolute_error: 56354.0078
- val_loss: 4.6229 - val_mean_absolute_error: 1.5681
Epoch 00045: saving model to /...
904/904 - 2s - loss: 1.3348 - mean_absolute_error: 0.7894 - val_loss: 2.2875
- val_mean_absolute_error: 1.1510
My model:
model = keras.Sequential()
model.add(keras.layers.LSTM(360, activation='relu', input_shape=(N_STEPS, n_features)))
model.add(keras.layers.Dropout(0.1))
model.add(keras.layers.Dense(1, activation='relu'))
model.compile(optimizer='adam', loss='mse', metrics=['mae'])
What is the cause of this?
Theoretically, it shouldn't be able to have such a high loss unless it outputs very high values for that epoch. Which is strange since the model's output makes sense during other epochs.
python keras regression lstm accuracy
asked 18 hours ago
1b151b15
12
New contributor
1b15 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
I am training an LSTM for time series forecasting and it has produced an extremly high loss value during one epoch:
Epoch 00043: saving model to /...
904/904 - 2s - loss: 0.7537 - mean_absolute_error: 0.5772 - val_loss: 1.4430
- val_mean_absolute_error: 0.7124
Epoch 00044: saving model to /...
904/904 - 2s - loss: 240372339275.7649 - mean_absolute_error: 56354.0078
- val_loss: 4.6229 - val_mean_absolute_error: 1.5681
Epoch 00045: saving model to /...
904/904 - 2s - loss: 1.3348 - mean_absolute_error: 0.7894 - val_loss: 2.2875
- val_mean_absolute_error: 1.1510
My model:
model = keras.Sequential()
model.add(keras.layers.LSTM(360, activation='relu', input_shape=(N_STEPS, n_features)))
model.add(keras.layers.Dropout(0.1))
model.add(keras.layers.Dense(1, activation='relu'))
model.compile(optimizer='adam', loss='mse', metrics=['mae'])
What is the cause of this?
Theoretically, it shouldn't be able to have such a high loss unless it outputs very high values for that epoch. Which is strange since the model's output makes sense during other epochs.
python keras regression lstm accuracy
asked 18 hours ago
1b151b15
12
New contributor
1b15 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
I am training an LSTM for time series forecasting and it has produced an extremly high loss value during one epoch:
Epoch 00043: saving model to /...
904/904 - 2s - loss: 0.7537 - mean_absolute_error: 0.5772 - val_loss: 1.4430
- val_mean_absolute_error: 0.7124
Epoch 00044: saving model to /...
904/904 - 2s - loss: 240372339275.7649 - mean_absolute_error: 56354.0078
- val_loss: 4.6229 - val_mean_absolute_error: 1.5681
Epoch 00045: saving model to /...
904/904 - 2s - loss: 1.3348 - mean_absolute_error: 0.7894 - val_loss: 2.2875
- val_mean_absolute_error: 1.1510
My model:
model = keras.Sequential()
model.add(keras.layers.LSTM(360, activation='relu', input_shape=(N_STEPS, n_features)))
model.add(keras.layers.Dropout(0.1))
model.add(keras.layers.Dense(1, activation='relu'))
model.compile(optimizer='adam', loss='mse', metrics=['mae'])
What is the cause of this?
Theoretically, it shouldn't be able to have such a high loss unless it outputs very high values for that epoch. Which is strange since the model's output makes sense during other epochs.
python keras regression lstm accuracy
asked 18 hours ago
1b151b15
12
New contributor
1b15 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
I am training an LSTM for time series forecasting and it has produced an extremly high loss value during one epoch:
Epoch 00043: saving model to /...
904/904 - 2s - loss: 0.7537 - mean_absolute_error: 0.5772 - val_loss: 1.4430
- val_mean_absolute_error: 0.7124
Epoch 00044: saving model to /...
904/904 - 2s - loss: 240372339275.7649 - mean_absolute_error: 56354.0078
- val_loss: 4.6229 - val_mean_absolute_error: 1.5681
Epoch 00045: saving model to /...
904/904 - 2s - loss: 1.3348 - mean_absolute_error: 0.7894 - val_loss: 2.2875
- val_mean_absolute_error: 1.1510
My model:
model = keras.Sequential()
model.add(keras.layers.LSTM(360, activation='relu', input_shape=(N_STEPS, n_features)))
model.add(keras.layers.Dropout(0.1))
model.add(keras.layers.Dense(1, activation='relu'))
model.compile(optimizer='adam', loss='mse', metrics=['mae'])
What is the cause of this?
Theoretically, it shouldn't be able to have such a high loss unless it outputs very high values for that epoch. Which is strange since the model's output makes sense during other epochs.
python keras regression lstm accuracy
python keras regression lstm accuracy
asked 18 hours ago
1b151b15
12
New contributor
1b15 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 18 hours ago
1b151b15
12
New contributor
1b15 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 18 hours ago
1b151b15
12
New contributor
1b15 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
asked 18 hours ago
1b151b15
12
asked 18 hours ago
1b151b15
12
12
New contributor
1b15 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
1b15 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
1b15 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
$begingroup$
Sorry I couldn't comment as it requires 50 Reputation. On Epoch 44 there is a huge spike in the loss. It is entirely possible that the model may have come across new data and it may have learned a few tricks up its sleeve. Try to plot loss of train & validation vs epoch to see if it underfits or overfits.
answered 14 hours ago
Hari_SheldonHari_Sheldon
31
New contributor
Hari_Sheldon is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
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
});
}
});
1b15 is a new contributor. Be nice, and check out our Code of Conduct.
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%2f46387%2fkeras-extreme-spike-in-loss-during-training%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
$begingroup$
Sorry I couldn't comment as it requires 50 Reputation. On Epoch 44 there is a huge spike in the loss. It is entirely possible that the model may have come across new data and it may have learned a few tricks up its sleeve. Try to plot loss of train & validation vs epoch to see if it underfits or overfits.
answered 14 hours ago
Hari_SheldonHari_Sheldon
31
New contributor
Hari_Sheldon is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
Sorry I couldn't comment as it requires 50 Reputation. On Epoch 44 there is a huge spike in the loss. It is entirely possible that the model may have come across new data and it may have learned a few tricks up its sleeve. Try to plot loss of train & validation vs epoch to see if it underfits or overfits.
answered 14 hours ago
Hari_SheldonHari_Sheldon
31
New contributor
Hari_Sheldon is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
add a comment |
$begingroup$
Sorry I couldn't comment as it requires 50 Reputation. On Epoch 44 there is a huge spike in the loss. It is entirely possible that the model may have come across new data and it may have learned a few tricks up its sleeve. Try to plot loss of train & validation vs epoch to see if it underfits or overfits.
answered 14 hours ago
Hari_SheldonHari_Sheldon
31
New contributor
Hari_Sheldon is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
$endgroup$
Sorry I couldn't comment as it requires 50 Reputation. On Epoch 44 there is a huge spike in the loss. It is entirely possible that the model may have come across new data and it may have learned a few tricks up its sleeve. Try to plot loss of train & validation vs epoch to see if it underfits or overfits.
answered 14 hours ago
Hari_SheldonHari_Sheldon
31
New contributor
Hari_Sheldon is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
answered 14 hours ago
Hari_SheldonHari_Sheldon
31
New contributor
Hari_Sheldon is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
answered 14 hours ago
Hari_SheldonHari_Sheldon
31
answered 14 hours ago
Hari_SheldonHari_Sheldon
31
31
New contributor
Hari_Sheldon is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
New contributor
Hari_Sheldon is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
Hari_Sheldon is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.
add a comment |
add a comment |
1b15 is a new contributor. Be nice, and check out our Code of Conduct.
1b15 is a new contributor. Be nice, and check out our Code of Conduct.
1b15 is a new contributor. Be nice, and check out our Code of Conduct.
1b15 is a new contributor. Be nice, and check out our Code of Conduct.
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%2f46387%2fkeras-extreme-spike-in-loss-during-training%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