How to retrieve elements from TensorFlow Hub / saved model?
I am using the hub.Module("https://tfhub.dev/google/universal-sentence-encoder/2") to restore a model. I want to retrieve the word embeddings and the look-up table of the trained model.
When using the full embedding model you can simply do:
embed = hub.Module("https://tfhub.dev/google/universal-sentence-encoder/2")
embeddings = embed([
"The quick brown fox jumps over the lazy dog.",
"I am a sentence for which I would like to get its embedding"])
with tf.Session() as sess:
sess.run([tf.global_variables_initializer(), tf.tables_initializer()])
print(sess.run(embeddings))
This then gives a pass through the full model. I simply want to pass the sentence until the words are encoded to their word_embedding at the very beginning. I have managed to retrieve the weights for the embeddings using:
E = sess.run(slim.get_variables('Embeddings_en:0'))
which gives a (N_words x N_embedding_size) matrix.
The problem is now I can't retrieve the vocabulary. I found operation nodes in the graph called module/string_to_index_Lookup/hash_table_Lookup which probably do what I want, but these are not variables (so to my limited understanding of low-level tensorflow) I was not able to reuse these operations directly.
How could this be solved?
Apparently it is not trivial to do it (https://github.com/tensorflow/hub/issues/67) - but maybe someone on here can help ;)
python tensorflow tensorflow-serving tensorflow-hub
edited Nov 17 '18 at 13:28
Ali AzG
581515
asked Nov 17 '18 at 13:23
Oliver Ebrle
577
add a comment |
I am using the hub.Module("https://tfhub.dev/google/universal-sentence-encoder/2") to restore a model. I want to retrieve the word embeddings and the look-up table of the trained model.
When using the full embedding model you can simply do:
embed = hub.Module("https://tfhub.dev/google/universal-sentence-encoder/2")
embeddings = embed([
"The quick brown fox jumps over the lazy dog.",
"I am a sentence for which I would like to get its embedding"])
with tf.Session() as sess:
sess.run([tf.global_variables_initializer(), tf.tables_initializer()])
print(sess.run(embeddings))
This then gives a pass through the full model. I simply want to pass the sentence until the words are encoded to their word_embedding at the very beginning. I have managed to retrieve the weights for the embeddings using:
E = sess.run(slim.get_variables('Embeddings_en:0'))
which gives a (N_words x N_embedding_size) matrix.
The problem is now I can't retrieve the vocabulary. I found operation nodes in the graph called module/string_to_index_Lookup/hash_table_Lookup which probably do what I want, but these are not variables (so to my limited understanding of low-level tensorflow) I was not able to reuse these operations directly.
How could this be solved?
Apparently it is not trivial to do it (https://github.com/tensorflow/hub/issues/67) - but maybe someone on here can help ;)
python tensorflow tensorflow-serving tensorflow-hub
edited Nov 17 '18 at 13:28
Ali AzG
581515
asked Nov 17 '18 at 13:23
Oliver Ebrle
577
add a comment |
I am using the hub.Module("https://tfhub.dev/google/universal-sentence-encoder/2") to restore a model. I want to retrieve the word embeddings and the look-up table of the trained model.
When using the full embedding model you can simply do:
embed = hub.Module("https://tfhub.dev/google/universal-sentence-encoder/2")
embeddings = embed([
"The quick brown fox jumps over the lazy dog.",
"I am a sentence for which I would like to get its embedding"])
with tf.Session() as sess:
sess.run([tf.global_variables_initializer(), tf.tables_initializer()])
print(sess.run(embeddings))
This then gives a pass through the full model. I simply want to pass the sentence until the words are encoded to their word_embedding at the very beginning. I have managed to retrieve the weights for the embeddings using:
E = sess.run(slim.get_variables('Embeddings_en:0'))
which gives a (N_words x N_embedding_size) matrix.
The problem is now I can't retrieve the vocabulary. I found operation nodes in the graph called module/string_to_index_Lookup/hash_table_Lookup which probably do what I want, but these are not variables (so to my limited understanding of low-level tensorflow) I was not able to reuse these operations directly.
How could this be solved?
Apparently it is not trivial to do it (https://github.com/tensorflow/hub/issues/67) - but maybe someone on here can help ;)
python tensorflow tensorflow-serving tensorflow-hub
edited Nov 17 '18 at 13:28
Ali AzG
581515
asked Nov 17 '18 at 13:23
Oliver Ebrle
577
I am using the hub.Module("https://tfhub.dev/google/universal-sentence-encoder/2") to restore a model. I want to retrieve the word embeddings and the look-up table of the trained model.
When using the full embedding model you can simply do:
embed = hub.Module("https://tfhub.dev/google/universal-sentence-encoder/2")
embeddings = embed([
"The quick brown fox jumps over the lazy dog.",
"I am a sentence for which I would like to get its embedding"])
with tf.Session() as sess:
sess.run([tf.global_variables_initializer(), tf.tables_initializer()])
print(sess.run(embeddings))
This then gives a pass through the full model. I simply want to pass the sentence until the words are encoded to their word_embedding at the very beginning. I have managed to retrieve the weights for the embeddings using:
E = sess.run(slim.get_variables('Embeddings_en:0'))
which gives a (N_words x N_embedding_size) matrix.
The problem is now I can't retrieve the vocabulary. I found operation nodes in the graph called module/string_to_index_Lookup/hash_table_Lookup which probably do what I want, but these are not variables (so to my limited understanding of low-level tensorflow) I was not able to reuse these operations directly.
How could this be solved?
Apparently it is not trivial to do it (https://github.com/tensorflow/hub/issues/67) - but maybe someone on here can help ;)
python tensorflow tensorflow-serving tensorflow-hub
python tensorflow tensorflow-serving tensorflow-hub
edited Nov 17 '18 at 13:28
Ali AzG
581515
asked Nov 17 '18 at 13:23
Oliver Ebrle
577
edited Nov 17 '18 at 13:28
Ali AzG
581515
asked Nov 17 '18 at 13:23
Oliver Ebrle
577
edited Nov 17 '18 at 13:28
Ali AzG
581515
edited Nov 17 '18 at 13:28
Ali AzG
581515
edited Nov 17 '18 at 13:28
Ali AzG
581515
581515
asked Nov 17 '18 at 13:23
Oliver Ebrle
577
asked Nov 17 '18 at 13:23
Oliver Ebrle
577
asked Nov 17 '18 at 13:23
Oliver Ebrle
577
577
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%2f53351665%2fhow-to-retrieve-elements-from-tensorflow-hub-saved-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.
Some of your past answers have not been well-received, and you're in danger of being blocked from answering.
Please pay close attention to the following guidance:
- 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%2f53351665%2fhow-to-retrieve-elements-from-tensorflow-hub-saved-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
