Keras LSTM training over multiple sequences












0















I am new to deep learning and trying to train a NN to predict a sequence Y_n given X_n, where Y_n is a number and X_n is a vector. Assume I have multiple training sequences (X_n, Y_n), each with different lengths, what is the best way of training? Below is my code, would this work or do I need something like reset state? My goal is to update the weights every time I feed a new training sequence, but I do not want the old training to be completely overwritten as well. Thanks.



inputD = len(feature)
model = Sequential()
model.add(LSTM(input_dim=inputD,output_dim=10,return_sequences=True))
model.add(LSTM(10,return_sequences=True))
model.add(Dense(5,activation='relu'))
model.add(Dense(5,activation='relu'))
model.add(Dense(1,activation='sigmoid'))
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
for j in range(5):
trainX = df[df['id'] == j][feature].values
trainY = df[df['id'] == j]['Y'].values
trainX = numpy.reshape(trainX, (1, trainX.shape[0], trainX.shape[1]))
trainY = numpy.reshape(trainY, (1, trainY.shape[0], 1))
model.fit(trainX, trainY, epochs=100, batch_size=50,verbose=2)









share|improve this question

























  • feature is a list of columns names in df

    – physcis_beginner
    Nov 25 '18 at 20:36
















0















I am new to deep learning and trying to train a NN to predict a sequence Y_n given X_n, where Y_n is a number and X_n is a vector. Assume I have multiple training sequences (X_n, Y_n), each with different lengths, what is the best way of training? Below is my code, would this work or do I need something like reset state? My goal is to update the weights every time I feed a new training sequence, but I do not want the old training to be completely overwritten as well. Thanks.



inputD = len(feature)
model = Sequential()
model.add(LSTM(input_dim=inputD,output_dim=10,return_sequences=True))
model.add(LSTM(10,return_sequences=True))
model.add(Dense(5,activation='relu'))
model.add(Dense(5,activation='relu'))
model.add(Dense(1,activation='sigmoid'))
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
for j in range(5):
trainX = df[df['id'] == j][feature].values
trainY = df[df['id'] == j]['Y'].values
trainX = numpy.reshape(trainX, (1, trainX.shape[0], trainX.shape[1]))
trainY = numpy.reshape(trainY, (1, trainY.shape[0], 1))
model.fit(trainX, trainY, epochs=100, batch_size=50,verbose=2)









share|improve this question

























  • feature is a list of columns names in df

    – physcis_beginner
    Nov 25 '18 at 20:36














0












0








0








I am new to deep learning and trying to train a NN to predict a sequence Y_n given X_n, where Y_n is a number and X_n is a vector. Assume I have multiple training sequences (X_n, Y_n), each with different lengths, what is the best way of training? Below is my code, would this work or do I need something like reset state? My goal is to update the weights every time I feed a new training sequence, but I do not want the old training to be completely overwritten as well. Thanks.



inputD = len(feature)
model = Sequential()
model.add(LSTM(input_dim=inputD,output_dim=10,return_sequences=True))
model.add(LSTM(10,return_sequences=True))
model.add(Dense(5,activation='relu'))
model.add(Dense(5,activation='relu'))
model.add(Dense(1,activation='sigmoid'))
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
for j in range(5):
trainX = df[df['id'] == j][feature].values
trainY = df[df['id'] == j]['Y'].values
trainX = numpy.reshape(trainX, (1, trainX.shape[0], trainX.shape[1]))
trainY = numpy.reshape(trainY, (1, trainY.shape[0], 1))
model.fit(trainX, trainY, epochs=100, batch_size=50,verbose=2)









share|improve this question
















I am new to deep learning and trying to train a NN to predict a sequence Y_n given X_n, where Y_n is a number and X_n is a vector. Assume I have multiple training sequences (X_n, Y_n), each with different lengths, what is the best way of training? Below is my code, would this work or do I need something like reset state? My goal is to update the weights every time I feed a new training sequence, but I do not want the old training to be completely overwritten as well. Thanks.



inputD = len(feature)
model = Sequential()
model.add(LSTM(input_dim=inputD,output_dim=10,return_sequences=True))
model.add(LSTM(10,return_sequences=True))
model.add(Dense(5,activation='relu'))
model.add(Dense(5,activation='relu'))
model.add(Dense(1,activation='sigmoid'))
model.compile(loss='binary_crossentropy',optimizer='adam',metrics=['accuracy'])
for j in range(5):
trainX = df[df['id'] == j][feature].values
trainY = df[df['id'] == j]['Y'].values
trainX = numpy.reshape(trainX, (1, trainX.shape[0], trainX.shape[1]))
trainY = numpy.reshape(trainY, (1, trainY.shape[0], 1))
model.fit(trainX, trainY, epochs=100, batch_size=50,verbose=2)






python tensorflow machine-learning keras lstm






share|improve this question















share|improve this question













share|improve this question




share|improve this question








edited Nov 26 '18 at 1:48







physcis_beginner

















asked Nov 25 '18 at 20:36









physcis_beginnerphyscis_beginner

34




34













  • feature is a list of columns names in df

    – physcis_beginner
    Nov 25 '18 at 20:36



















  • feature is a list of columns names in df

    – physcis_beginner
    Nov 25 '18 at 20:36

















feature is a list of columns names in df

– physcis_beginner
Nov 25 '18 at 20:36





feature is a list of columns names in df

– physcis_beginner
Nov 25 '18 at 20:36












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%2f53471698%2fkeras-lstm-training-over-multiple-sequences%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%2f53471698%2fkeras-lstm-training-over-multiple-sequences%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

Costa Masnaga

Fotorealismo

Sidney Franklin