How to prevent overfitting in Keras sequential model?
0
I am already adding dropout regularization. I am trying to build a multiclass text classification multilayer perceptron model.
My model:
model = Sequential([
Dropout(rate=0.2, input_shape=features),
Dense(units=64, activation='relu'),
Dropout(rate=0.2),
Dense(units=64, activation='relu'),
Dropout(rate=0.2),
Dense(units=16, activation='softmax')])
My model.summary():
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dropout_1 (Dropout) (None, 20000) 0
_________________________________________________________________
dense_1 (Dense) (None, 64) 1280064
_________________________________________________________________
dropout_2 (Dropout) (None, 64) 0
_________________________________________________________________
dense_2 (Dense) (None, 64) 4160
_________________________________________________________________
dropout_3 (Dropout) (None, 64) 0
_________________________________________________________________
dense_3 (Dense) (None, 16) 1040
=================================================================
Total params: 1,285,264
Trainable params: 1,285,264
Non-trainable params: 0
_________________________________________________________________
None
Train on 6940 samples, validate on 1735 samples
I am getting:
Epoch 16/1000
- 4s - loss: 0.4926 - acc: 0.8719 - val_loss: 1.2640 - val_acc: 0.6640
Validation accuracy: 0.6639769498140736, loss: 1.2639631692545559
The validation accuracy is ~20% less than the accuracy, and the validation loss is way higher than the training loss.
I am already using dropout regularization, and using epochs = 1000, batch size = 512 and early stopping on val_loss.
Any suggestions?
python machine-learning scikit-learn keras text-classification
edited Nov 15 '18 at 1:20
Milo Lu
1,61911527
asked Nov 15 '18 at 0:48
Ahmed El GoharyAhmed El Gohary
263
|
show 1 more comment
0
I am already adding dropout regularization. I am trying to build a multiclass text classification multilayer perceptron model.
My model:
model = Sequential([
Dropout(rate=0.2, input_shape=features),
Dense(units=64, activation='relu'),
Dropout(rate=0.2),
Dense(units=64, activation='relu'),
Dropout(rate=0.2),
Dense(units=16, activation='softmax')])
My model.summary():
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dropout_1 (Dropout) (None, 20000) 0
_________________________________________________________________
dense_1 (Dense) (None, 64) 1280064
_________________________________________________________________
dropout_2 (Dropout) (None, 64) 0
_________________________________________________________________
dense_2 (Dense) (None, 64) 4160
_________________________________________________________________
dropout_3 (Dropout) (None, 64) 0
_________________________________________________________________
dense_3 (Dense) (None, 16) 1040
=================================================================
Total params: 1,285,264
Trainable params: 1,285,264
Non-trainable params: 0
_________________________________________________________________
None
Train on 6940 samples, validate on 1735 samples
I am getting:
Epoch 16/1000
- 4s - loss: 0.4926 - acc: 0.8719 - val_loss: 1.2640 - val_acc: 0.6640
Validation accuracy: 0.6639769498140736, loss: 1.2639631692545559
The validation accuracy is ~20% less than the accuracy, and the validation loss is way higher than the training loss.
I am already using dropout regularization, and using epochs = 1000, batch size = 512 and early stopping on val_loss.
Any suggestions?
python machine-learning scikit-learn keras text-classification
edited Nov 15 '18 at 1:20
Milo Lu
1,61911527
asked Nov 15 '18 at 0:48
Ahmed El GoharyAhmed El Gohary
263
Could you please also add a code how do you run model.fit( ... ).
– Danylo Baibak
Nov 15 '18 at 7:29
Would also need how you are doing the preprocessing on training and validation data if any
– Vivek Kumar
Nov 15 '18 at 8:09
@DanyloBaibak As I said, epochs = 1000, batch size = 512, verbose = 2, rest are just my local variables.
– Ahmed El Gohary
Nov 15 '18 at 22:49
@VivekKumar, tokenized the text as unigrams and bigrams and vectorizing using tf-idf, then i SelectKBest 20,000 features
– Ahmed El Gohary
Nov 15 '18 at 22:50
@AhmedElGohary, do you have some validation dataset? The easiest way ismodel.fit( ...., validation_split=0.1)
– Danylo Baibak
Nov 16 '18 at 8:50
|
show 1 more comment
0
0
0
I am already adding dropout regularization. I am trying to build a multiclass text classification multilayer perceptron model.
My model:
model = Sequential([
Dropout(rate=0.2, input_shape=features),
Dense(units=64, activation='relu'),
Dropout(rate=0.2),
Dense(units=64, activation='relu'),
Dropout(rate=0.2),
Dense(units=16, activation='softmax')])
My model.summary():
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dropout_1 (Dropout) (None, 20000) 0
_________________________________________________________________
dense_1 (Dense) (None, 64) 1280064
_________________________________________________________________
dropout_2 (Dropout) (None, 64) 0
_________________________________________________________________
dense_2 (Dense) (None, 64) 4160
_________________________________________________________________
dropout_3 (Dropout) (None, 64) 0
_________________________________________________________________
dense_3 (Dense) (None, 16) 1040
=================================================================
Total params: 1,285,264
Trainable params: 1,285,264
Non-trainable params: 0
_________________________________________________________________
None
Train on 6940 samples, validate on 1735 samples
I am getting:
Epoch 16/1000
- 4s - loss: 0.4926 - acc: 0.8719 - val_loss: 1.2640 - val_acc: 0.6640
Validation accuracy: 0.6639769498140736, loss: 1.2639631692545559
The validation accuracy is ~20% less than the accuracy, and the validation loss is way higher than the training loss.
I am already using dropout regularization, and using epochs = 1000, batch size = 512 and early stopping on val_loss.
Any suggestions?
python machine-learning scikit-learn keras text-classification
edited Nov 15 '18 at 1:20
Milo Lu
1,61911527
asked Nov 15 '18 at 0:48
Ahmed El GoharyAhmed El Gohary
263
I am already adding dropout regularization. I am trying to build a multiclass text classification multilayer perceptron model.
My model:
model = Sequential([
Dropout(rate=0.2, input_shape=features),
Dense(units=64, activation='relu'),
Dropout(rate=0.2),
Dense(units=64, activation='relu'),
Dropout(rate=0.2),
Dense(units=16, activation='softmax')])
My model.summary():
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dropout_1 (Dropout) (None, 20000) 0
_________________________________________________________________
dense_1 (Dense) (None, 64) 1280064
_________________________________________________________________
dropout_2 (Dropout) (None, 64) 0
_________________________________________________________________
dense_2 (Dense) (None, 64) 4160
_________________________________________________________________
dropout_3 (Dropout) (None, 64) 0
_________________________________________________________________
dense_3 (Dense) (None, 16) 1040
=================================================================
Total params: 1,285,264
Trainable params: 1,285,264
Non-trainable params: 0
_________________________________________________________________
None
Train on 6940 samples, validate on 1735 samples
I am getting:
Epoch 16/1000
- 4s - loss: 0.4926 - acc: 0.8719 - val_loss: 1.2640 - val_acc: 0.6640
Validation accuracy: 0.6639769498140736, loss: 1.2639631692545559
The validation accuracy is ~20% less than the accuracy, and the validation loss is way higher than the training loss.
I am already using dropout regularization, and using epochs = 1000, batch size = 512 and early stopping on val_loss.
Any suggestions?
python machine-learning scikit-learn keras text-classification
python machine-learning scikit-learn keras text-classification
edited Nov 15 '18 at 1:20
Milo Lu
1,61911527
asked Nov 15 '18 at 0:48
Ahmed El GoharyAhmed El Gohary
263
edited Nov 15 '18 at 1:20
Milo Lu
1,61911527
asked Nov 15 '18 at 0:48
Ahmed El GoharyAhmed El Gohary
263
edited Nov 15 '18 at 1:20
Milo Lu
1,61911527
edited Nov 15 '18 at 1:20
Milo Lu
1,61911527
edited Nov 15 '18 at 1:20
Milo Lu
1,61911527
1,61911527
asked Nov 15 '18 at 0:48
Ahmed El GoharyAhmed El Gohary
263
asked Nov 15 '18 at 0:48
Ahmed El GoharyAhmed El Gohary
263
asked Nov 15 '18 at 0:48
Ahmed El GoharyAhmed El Gohary
263
263
Could you please also add a code how do you run model.fit( ... ).
– Danylo Baibak
Nov 15 '18 at 7:29
Would also need how you are doing the preprocessing on training and validation data if any
– Vivek Kumar
Nov 15 '18 at 8:09
@DanyloBaibak As I said, epochs = 1000, batch size = 512, verbose = 2, rest are just my local variables.
– Ahmed El Gohary
Nov 15 '18 at 22:49
@VivekKumar, tokenized the text as unigrams and bigrams and vectorizing using tf-idf, then i SelectKBest 20,000 features
– Ahmed El Gohary
Nov 15 '18 at 22:50
@AhmedElGohary, do you have some validation dataset? The easiest way ismodel.fit( ...., validation_split=0.1)
– Danylo Baibak
Nov 16 '18 at 8:50
|
show 1 more comment
Could you please also add a code how do you run model.fit( ... ).
– Danylo Baibak
Nov 15 '18 at 7:29
Would also need how you are doing the preprocessing on training and validation data if any
– Vivek Kumar
Nov 15 '18 at 8:09
@DanyloBaibak As I said, epochs = 1000, batch size = 512, verbose = 2, rest are just my local variables.
– Ahmed El Gohary
Nov 15 '18 at 22:49
@VivekKumar, tokenized the text as unigrams and bigrams and vectorizing using tf-idf, then i SelectKBest 20,000 features
– Ahmed El Gohary
Nov 15 '18 at 22:50
@AhmedElGohary, do you have some validation dataset? The easiest way ismodel.fit( ...., validation_split=0.1)
– Danylo Baibak
Nov 16 '18 at 8:50
Could you please also add a code how do you run model.fit( ... ).
– Danylo Baibak
Nov 15 '18 at 7:29
Could you please also add a code how do you run model.fit( ... ).
– Danylo Baibak
Nov 15 '18 at 7:29
Would also need how you are doing the preprocessing on training and validation data if any
– Vivek Kumar
Nov 15 '18 at 8:09
Would also need how you are doing the preprocessing on training and validation data if any
– Vivek Kumar
Nov 15 '18 at 8:09
@DanyloBaibak As I said, epochs = 1000, batch size = 512, verbose = 2, rest are just my local variables.
– Ahmed El Gohary
Nov 15 '18 at 22:49
@DanyloBaibak As I said, epochs = 1000, batch size = 512, verbose = 2, rest are just my local variables.
– Ahmed El Gohary
Nov 15 '18 at 22:49
@VivekKumar, tokenized the text as unigrams and bigrams and vectorizing using tf-idf, then i SelectKBest 20,000 features
– Ahmed El Gohary
Nov 15 '18 at 22:50
@VivekKumar, tokenized the text as unigrams and bigrams and vectorizing using tf-idf, then i SelectKBest 20,000 features
– Ahmed El Gohary
Nov 15 '18 at 22:50
@AhmedElGohary, do you have some validation dataset? The easiest way is
model.fit( ...., validation_split=0.1)– Danylo Baibak
Nov 16 '18 at 8:50
@AhmedElGohary, do you have some validation dataset? The easiest way is
model.fit( ...., validation_split=0.1)– Danylo Baibak
Nov 16 '18 at 8:50
|
show 1 more 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
});
}
});
draft saved
draft discarded
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%2f53310915%2fhow-to-prevent-overfitting-in-keras-sequential-model%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
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%2f53310915%2fhow-to-prevent-overfitting-in-keras-sequential-model%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
Could you please also add a code how do you run model.fit( ... ).
– Danylo Baibak
Nov 15 '18 at 7:29
Would also need how you are doing the preprocessing on training and validation data if any
– Vivek Kumar
Nov 15 '18 at 8:09
@DanyloBaibak As I said, epochs = 1000, batch size = 512, verbose = 2, rest are just my local variables.
– Ahmed El Gohary
Nov 15 '18 at 22:49
@VivekKumar, tokenized the text as unigrams and bigrams and vectorizing using tf-idf, then i SelectKBest 20,000 features
– Ahmed El Gohary
Nov 15 '18 at 22:50
@AhmedElGohary, do you have some validation dataset? The easiest way is
model.fit( ...., validation_split=0.1)– Danylo Baibak
Nov 16 '18 at 8:50