Keras Lambda Layer for calculating temperature in LSTM model
I have a problem with Keras Lambda Layers. I'm using Keras functional API to create my model. Also, I'd like to save the model to an h5 file.
It works perfectly with this code:
shared_layer = LSTM(size, return_sequences=True, dropout=self.params['dropout'][0], recurrent_dropout=self.params['dropout'][1])(shared_layer)
output = shared_layer
output = TimeDistributed(Dense(n_class_labels, activation='softmax'), name=modelName+'_softmax')(output)
But if I add the following line I get an error when saving the model. Though it doesn't throw an error when training:
logits_temperature = Lambda(lambda x : x / self.params['temperature'])(output)
output = TimeDistributed(Dense(n_class_labels, activation='softmax'), name=modelName+'_softmax')(logits_temperature)
Here's the error I get when saving:
TypeError: cannot serialize '_io.TextIOWrapper' object
lambda keras lstm layer temperature
edited Jan 20 at 10:08
Tomka Koliada
320327
asked Jan 20 at 9:58
JurekJurek
35
add a comment |
I have a problem with Keras Lambda Layers. I'm using Keras functional API to create my model. Also, I'd like to save the model to an h5 file.
It works perfectly with this code:
shared_layer = LSTM(size, return_sequences=True, dropout=self.params['dropout'][0], recurrent_dropout=self.params['dropout'][1])(shared_layer)
output = shared_layer
output = TimeDistributed(Dense(n_class_labels, activation='softmax'), name=modelName+'_softmax')(output)
But if I add the following line I get an error when saving the model. Though it doesn't throw an error when training:
logits_temperature = Lambda(lambda x : x / self.params['temperature'])(output)
output = TimeDistributed(Dense(n_class_labels, activation='softmax'), name=modelName+'_softmax')(logits_temperature)
Here's the error I get when saving:
TypeError: cannot serialize '_io.TextIOWrapper' object
lambda keras lstm layer temperature
edited Jan 20 at 10:08
Tomka Koliada
320327
asked Jan 20 at 9:58
JurekJurek
35
add a comment |
I have a problem with Keras Lambda Layers. I'm using Keras functional API to create my model. Also, I'd like to save the model to an h5 file.
It works perfectly with this code:
shared_layer = LSTM(size, return_sequences=True, dropout=self.params['dropout'][0], recurrent_dropout=self.params['dropout'][1])(shared_layer)
output = shared_layer
output = TimeDistributed(Dense(n_class_labels, activation='softmax'), name=modelName+'_softmax')(output)
But if I add the following line I get an error when saving the model. Though it doesn't throw an error when training:
logits_temperature = Lambda(lambda x : x / self.params['temperature'])(output)
output = TimeDistributed(Dense(n_class_labels, activation='softmax'), name=modelName+'_softmax')(logits_temperature)
Here's the error I get when saving:
TypeError: cannot serialize '_io.TextIOWrapper' object
lambda keras lstm layer temperature
edited Jan 20 at 10:08
Tomka Koliada
320327
asked Jan 20 at 9:58
JurekJurek
35
I have a problem with Keras Lambda Layers. I'm using Keras functional API to create my model. Also, I'd like to save the model to an h5 file.
It works perfectly with this code:
shared_layer = LSTM(size, return_sequences=True, dropout=self.params['dropout'][0], recurrent_dropout=self.params['dropout'][1])(shared_layer)
output = shared_layer
output = TimeDistributed(Dense(n_class_labels, activation='softmax'), name=modelName+'_softmax')(output)
But if I add the following line I get an error when saving the model. Though it doesn't throw an error when training:
logits_temperature = Lambda(lambda x : x / self.params['temperature'])(output)
output = TimeDistributed(Dense(n_class_labels, activation='softmax'), name=modelName+'_softmax')(logits_temperature)
Here's the error I get when saving:
TypeError: cannot serialize '_io.TextIOWrapper' object
lambda keras lstm layer temperature
lambda keras lstm layer temperature
edited Jan 20 at 10:08
Tomka Koliada
320327
asked Jan 20 at 9:58
JurekJurek
35
edited Jan 20 at 10:08
Tomka Koliada
320327
asked Jan 20 at 9:58
JurekJurek
35
edited Jan 20 at 10:08
Tomka Koliada
320327
edited Jan 20 at 10:08
Tomka Koliada
320327
edited Jan 20 at 10:08
Tomka Koliada
320327
320327
asked Jan 20 at 9:58
JurekJurek
35
asked Jan 20 at 9:58
JurekJurek
35
asked Jan 20 at 9:58
JurekJurek
35
35
add a comment |
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
});
}
});
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%2f54275304%2fkeras-lambda-layer-for-calculating-temperature-in-lstm-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
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.
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%2f54275304%2fkeras-lambda-layer-for-calculating-temperature-in-lstm-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
