Getting different loss when evaluating the training set in lstm model using keras
0
I am training a LSTM model using stock market data. When I train the model using "model.fit()", I get some loss values. However, when I evaluate the model using the same training set, the loss value is different from the best loss value during training process. Can anyone point out where I am making the mistake? Code is as follows.
def create_model(optimizer,num_neurons,input_timesteps,batch_size,input_dims):
model = Sequential()
model.add (LSTM (num_neurons,activation = 'tanh',dropout=0.2,stateful=True,
return_sequences=True, batch_input_shape =(batch_size,input_timesteps, input_dims) ))
model.add (LSTM (num_neurons,activation = 'tanh',dropout=0.2,stateful=True,
return_sequences=False, batch_input_shape =(batch_size,input_timesteps, input_dims) ))
model.add(Dense(1, activation='linear'))
model.compile(loss='mean_squared_error', optimizer=optimizer)
return model
erl_stop = EarlyStopping( monitor='val_loss', mode='min',restore_best_weights=True)
model.fit(x_train,y_train,epochs=num_epochs,batch_size=c['batch_size'],shuffle=False,callbacks=[erl_stop])
train_score=model.evaluate(x_train,y_train,batch_size=c['batch_size'])
python keras lstm
asked Nov 27 '18 at 4:46
SumanSuman
198
add a comment |
0
I am training a LSTM model using stock market data. When I train the model using "model.fit()", I get some loss values. However, when I evaluate the model using the same training set, the loss value is different from the best loss value during training process. Can anyone point out where I am making the mistake? Code is as follows.
def create_model(optimizer,num_neurons,input_timesteps,batch_size,input_dims):
model = Sequential()
model.add (LSTM (num_neurons,activation = 'tanh',dropout=0.2,stateful=True,
return_sequences=True, batch_input_shape =(batch_size,input_timesteps, input_dims) ))
model.add (LSTM (num_neurons,activation = 'tanh',dropout=0.2,stateful=True,
return_sequences=False, batch_input_shape =(batch_size,input_timesteps, input_dims) ))
model.add(Dense(1, activation='linear'))
model.compile(loss='mean_squared_error', optimizer=optimizer)
return model
erl_stop = EarlyStopping( monitor='val_loss', mode='min',restore_best_weights=True)
model.fit(x_train,y_train,epochs=num_epochs,batch_size=c['batch_size'],shuffle=False,callbacks=[erl_stop])
train_score=model.evaluate(x_train,y_train,batch_size=c['batch_size'])
python keras lstm
asked Nov 27 '18 at 4:46
SumanSuman
198
2
This is completely normal, your network has Dropout, which doesn't behave the same during training and during inference. When you evaluate the model, you are doing inference, so the loss isn't the same.
– Matias Valdenegro
Nov 27 '18 at 9:26
add a comment |
0
0
0
I am training a LSTM model using stock market data. When I train the model using "model.fit()", I get some loss values. However, when I evaluate the model using the same training set, the loss value is different from the best loss value during training process. Can anyone point out where I am making the mistake? Code is as follows.
def create_model(optimizer,num_neurons,input_timesteps,batch_size,input_dims):
model = Sequential()
model.add (LSTM (num_neurons,activation = 'tanh',dropout=0.2,stateful=True,
return_sequences=True, batch_input_shape =(batch_size,input_timesteps, input_dims) ))
model.add (LSTM (num_neurons,activation = 'tanh',dropout=0.2,stateful=True,
return_sequences=False, batch_input_shape =(batch_size,input_timesteps, input_dims) ))
model.add(Dense(1, activation='linear'))
model.compile(loss='mean_squared_error', optimizer=optimizer)
return model
erl_stop = EarlyStopping( monitor='val_loss', mode='min',restore_best_weights=True)
model.fit(x_train,y_train,epochs=num_epochs,batch_size=c['batch_size'],shuffle=False,callbacks=[erl_stop])
train_score=model.evaluate(x_train,y_train,batch_size=c['batch_size'])
python keras lstm
asked Nov 27 '18 at 4:46
SumanSuman
198
I am training a LSTM model using stock market data. When I train the model using "model.fit()", I get some loss values. However, when I evaluate the model using the same training set, the loss value is different from the best loss value during training process. Can anyone point out where I am making the mistake? Code is as follows.
def create_model(optimizer,num_neurons,input_timesteps,batch_size,input_dims):
model = Sequential()
model.add (LSTM (num_neurons,activation = 'tanh',dropout=0.2,stateful=True,
return_sequences=True, batch_input_shape =(batch_size,input_timesteps, input_dims) ))
model.add (LSTM (num_neurons,activation = 'tanh',dropout=0.2,stateful=True,
return_sequences=False, batch_input_shape =(batch_size,input_timesteps, input_dims) ))
model.add(Dense(1, activation='linear'))
model.compile(loss='mean_squared_error', optimizer=optimizer)
return model
erl_stop = EarlyStopping( monitor='val_loss', mode='min',restore_best_weights=True)
model.fit(x_train,y_train,epochs=num_epochs,batch_size=c['batch_size'],shuffle=False,callbacks=[erl_stop])
train_score=model.evaluate(x_train,y_train,batch_size=c['batch_size'])
python keras lstm
python keras lstm
asked Nov 27 '18 at 4:46
SumanSuman
198
asked Nov 27 '18 at 4:46
SumanSuman
198
edited Nov 27 '18 at 6:46
Suman
asked Nov 27 '18 at 4:46
SumanSuman
198
asked Nov 27 '18 at 4:46
SumanSuman
198
asked Nov 27 '18 at 4:46
SumanSuman
198
198
2
This is completely normal, your network has Dropout, which doesn't behave the same during training and during inference. When you evaluate the model, you are doing inference, so the loss isn't the same.
– Matias Valdenegro
Nov 27 '18 at 9:26
add a comment |
2
This is completely normal, your network has Dropout, which doesn't behave the same during training and during inference. When you evaluate the model, you are doing inference, so the loss isn't the same.
– Matias Valdenegro
Nov 27 '18 at 9:26
2
2
This is completely normal, your network has Dropout, which doesn't behave the same during training and during inference. When you evaluate the model, you are doing inference, so the loss isn't the same.
– Matias Valdenegro
Nov 27 '18 at 9:26
This is completely normal, your network has Dropout, which doesn't behave the same during training and during inference. When you evaluate the model, you are doing inference, so the loss isn't the same.
– Matias Valdenegro
Nov 27 '18 at 9:26
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
});
}
});
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%2f53492918%2fgetting-different-loss-when-evaluating-the-training-set-in-lstm-model-using-kera%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%2f53492918%2fgetting-different-loss-when-evaluating-the-training-set-in-lstm-model-using-kera%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
2
This is completely normal, your network has Dropout, which doesn't behave the same during training and during inference. When you evaluate the model, you are doing inference, so the loss isn't the same.
– Matias Valdenegro
Nov 27 '18 at 9:26