What should be the correct dimension of output of attention layer?
.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty{ height:90px;width:728px;box-sizing:border-box;
}
I building a LSTM+attention layer model. According to my understanding attention layer assigns weights to each word of the input sequence. Therefore, the output of attention layer should be (None,280). However, I am getting (None,240), which means that attention layer is learning attention over hidden states of the LSTM.
Where am I going wrong here?
MAX_SEQUENCE_LENGTH=140
EMBEDDING_DIM = 300
model = Sequential()
model.add(Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=False))
model.add(Bidirectional(CuDNNLSTM(120, return_sequences=True), input_shape=
(train_X.shape[1], EMBEDDING_DIM)))
model.add(Attention(MAX_SEQUENCE_LENGTH))
# model.add(Flatten())
model.add(Dense(100,activation='relu'))
model.add(Dense(1, activation='sigmoid'))
print(model.summary())
Layer (type) --- Output Shape --- Param #
embedding_1 (Embedding) ---- (None, 140, 300) --- 45720000
bidirectional_1 (Bidirection (None, 140, 240) --- 405120
attention_1 (Attention) --- (None, 240) --- 380
dense_1 (Dense) --- (None, 100) --- 24100
dense_2 (Dense) --- (None, 1) --- 101
Total params: 46,149,701
Trainable params: 429,701
Non-trainable params: 45,720,000
None
deep-learning attention-model
asked Jan 4 at 7:48
Samarth AgrawalSamarth Agrawal
33
add a comment |
I building a LSTM+attention layer model. According to my understanding attention layer assigns weights to each word of the input sequence. Therefore, the output of attention layer should be (None,280). However, I am getting (None,240), which means that attention layer is learning attention over hidden states of the LSTM.
Where am I going wrong here?
MAX_SEQUENCE_LENGTH=140
EMBEDDING_DIM = 300
model = Sequential()
model.add(Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=False))
model.add(Bidirectional(CuDNNLSTM(120, return_sequences=True), input_shape=
(train_X.shape[1], EMBEDDING_DIM)))
model.add(Attention(MAX_SEQUENCE_LENGTH))
# model.add(Flatten())
model.add(Dense(100,activation='relu'))
model.add(Dense(1, activation='sigmoid'))
print(model.summary())
Layer (type) --- Output Shape --- Param #
embedding_1 (Embedding) ---- (None, 140, 300) --- 45720000
bidirectional_1 (Bidirection (None, 140, 240) --- 405120
attention_1 (Attention) --- (None, 240) --- 380
dense_1 (Dense) --- (None, 100) --- 24100
dense_2 (Dense) --- (None, 1) --- 101
Total params: 46,149,701
Trainable params: 429,701
Non-trainable params: 45,720,000
None
deep-learning attention-model
asked Jan 4 at 7:48
Samarth AgrawalSamarth Agrawal
33
did you get the answer to your question?
– sariii
9 hours ago
add a comment |
I building a LSTM+attention layer model. According to my understanding attention layer assigns weights to each word of the input sequence. Therefore, the output of attention layer should be (None,280). However, I am getting (None,240), which means that attention layer is learning attention over hidden states of the LSTM.
Where am I going wrong here?
MAX_SEQUENCE_LENGTH=140
EMBEDDING_DIM = 300
model = Sequential()
model.add(Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=False))
model.add(Bidirectional(CuDNNLSTM(120, return_sequences=True), input_shape=
(train_X.shape[1], EMBEDDING_DIM)))
model.add(Attention(MAX_SEQUENCE_LENGTH))
# model.add(Flatten())
model.add(Dense(100,activation='relu'))
model.add(Dense(1, activation='sigmoid'))
print(model.summary())
Layer (type) --- Output Shape --- Param #
embedding_1 (Embedding) ---- (None, 140, 300) --- 45720000
bidirectional_1 (Bidirection (None, 140, 240) --- 405120
attention_1 (Attention) --- (None, 240) --- 380
dense_1 (Dense) --- (None, 100) --- 24100
dense_2 (Dense) --- (None, 1) --- 101
Total params: 46,149,701
Trainable params: 429,701
Non-trainable params: 45,720,000
None
deep-learning attention-model
asked Jan 4 at 7:48
Samarth AgrawalSamarth Agrawal
33
I building a LSTM+attention layer model. According to my understanding attention layer assigns weights to each word of the input sequence. Therefore, the output of attention layer should be (None,280). However, I am getting (None,240), which means that attention layer is learning attention over hidden states of the LSTM.
Where am I going wrong here?
MAX_SEQUENCE_LENGTH=140
EMBEDDING_DIM = 300
model = Sequential()
model.add(Embedding(len(word_index) + 1,
EMBEDDING_DIM,
weights=[embedding_matrix],
input_length=MAX_SEQUENCE_LENGTH,
trainable=False))
model.add(Bidirectional(CuDNNLSTM(120, return_sequences=True), input_shape=
(train_X.shape[1], EMBEDDING_DIM)))
model.add(Attention(MAX_SEQUENCE_LENGTH))
# model.add(Flatten())
model.add(Dense(100,activation='relu'))
model.add(Dense(1, activation='sigmoid'))
print(model.summary())
Layer (type) --- Output Shape --- Param #
embedding_1 (Embedding) ---- (None, 140, 300) --- 45720000
bidirectional_1 (Bidirection (None, 140, 240) --- 405120
attention_1 (Attention) --- (None, 240) --- 380
dense_1 (Dense) --- (None, 100) --- 24100
dense_2 (Dense) --- (None, 1) --- 101
Total params: 46,149,701
Trainable params: 429,701
Non-trainable params: 45,720,000
None
deep-learning attention-model
deep-learning attention-model
asked Jan 4 at 7:48
Samarth AgrawalSamarth Agrawal
33
asked Jan 4 at 7:48
Samarth AgrawalSamarth Agrawal
33
asked Jan 4 at 7:48
Samarth AgrawalSamarth Agrawal
33
asked Jan 4 at 7:48
Samarth AgrawalSamarth Agrawal
33
asked Jan 4 at 7:48
Samarth AgrawalSamarth Agrawal
33
33
did you get the answer to your question?
– sariii
9 hours ago
add a comment |
did you get the answer to your question?
– sariii
9 hours ago
did you get the answer to your question?
– sariii
9 hours ago
did you get the answer to your question?
– sariii
9 hours ago
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%2f54034935%2fwhat-should-be-the-correct-dimension-of-output-of-attention-layer%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%2f54034935%2fwhat-should-be-the-correct-dimension-of-output-of-attention-layer%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
did you get the answer to your question?
– sariii
9 hours ago