KeyError in freeze model










0















I've used the TensorFlow's graph_util.convert_variables_to_constants function to freeze a ckpt model. I have added all nodes in the ckpt model to the whitelist of the convert_variables_to_constants.



However, when I want to load the freezed model and use it, apparently a few nodes have not been added. I mean in the bellow line:



logits = tf.get_default_graph().get_tensor_by_name("Logits/BiasAdd:0")



it gives me the following error:



KeyError: "The name 'Logits/BiasAdd:0' refers to a Tensor which does not exist. The operation, 'Logits/BiasAdd', does not exist in the graph."


Any ideas how can I add this node to the freezed model?










share|improve this question



















  • 1





    convert_variables_to_constants prunes the graph and removes everything not needed to compute the given outputs (using extract_sub_graph). Make sure that all the nodes you want are necessary for the given outputs, or otherwise you can directly add more nodes as outputs to make sure they get included.

    – jdehesa
    Nov 13 '18 at 11:30












  • @jdehesa thanks. How can I include a necessary node to the output graph?

    – mohamad danesh
    Nov 13 '18 at 16:48











  • When you call convert_variables_to_constants, add the nodes you want to include to output_node_names.

    – jdehesa
    Nov 13 '18 at 16:50















0















I've used the TensorFlow's graph_util.convert_variables_to_constants function to freeze a ckpt model. I have added all nodes in the ckpt model to the whitelist of the convert_variables_to_constants.



However, when I want to load the freezed model and use it, apparently a few nodes have not been added. I mean in the bellow line:



logits = tf.get_default_graph().get_tensor_by_name("Logits/BiasAdd:0")



it gives me the following error:



KeyError: "The name 'Logits/BiasAdd:0' refers to a Tensor which does not exist. The operation, 'Logits/BiasAdd', does not exist in the graph."


Any ideas how can I add this node to the freezed model?










share|improve this question



















  • 1





    convert_variables_to_constants prunes the graph and removes everything not needed to compute the given outputs (using extract_sub_graph). Make sure that all the nodes you want are necessary for the given outputs, or otherwise you can directly add more nodes as outputs to make sure they get included.

    – jdehesa
    Nov 13 '18 at 11:30












  • @jdehesa thanks. How can I include a necessary node to the output graph?

    – mohamad danesh
    Nov 13 '18 at 16:48











  • When you call convert_variables_to_constants, add the nodes you want to include to output_node_names.

    – jdehesa
    Nov 13 '18 at 16:50













0












0








0








I've used the TensorFlow's graph_util.convert_variables_to_constants function to freeze a ckpt model. I have added all nodes in the ckpt model to the whitelist of the convert_variables_to_constants.



However, when I want to load the freezed model and use it, apparently a few nodes have not been added. I mean in the bellow line:



logits = tf.get_default_graph().get_tensor_by_name("Logits/BiasAdd:0")



it gives me the following error:



KeyError: "The name 'Logits/BiasAdd:0' refers to a Tensor which does not exist. The operation, 'Logits/BiasAdd', does not exist in the graph."


Any ideas how can I add this node to the freezed model?










share|improve this question
















I've used the TensorFlow's graph_util.convert_variables_to_constants function to freeze a ckpt model. I have added all nodes in the ckpt model to the whitelist of the convert_variables_to_constants.



However, when I want to load the freezed model and use it, apparently a few nodes have not been added. I mean in the bellow line:



logits = tf.get_default_graph().get_tensor_by_name("Logits/BiasAdd:0")



it gives me the following error:



KeyError: "The name 'Logits/BiasAdd:0' refers to a Tensor which does not exist. The operation, 'Logits/BiasAdd', does not exist in the graph."


Any ideas how can I add this node to the freezed model?







python tensorflow






share|improve this question















share|improve this question













share|improve this question




share|improve this question








edited Nov 13 '18 at 11:25









jdehesa

23.6k43454




23.6k43454










asked Nov 13 '18 at 7:50









mohamad daneshmohamad danesh

3511




3511







  • 1





    convert_variables_to_constants prunes the graph and removes everything not needed to compute the given outputs (using extract_sub_graph). Make sure that all the nodes you want are necessary for the given outputs, or otherwise you can directly add more nodes as outputs to make sure they get included.

    – jdehesa
    Nov 13 '18 at 11:30












  • @jdehesa thanks. How can I include a necessary node to the output graph?

    – mohamad danesh
    Nov 13 '18 at 16:48











  • When you call convert_variables_to_constants, add the nodes you want to include to output_node_names.

    – jdehesa
    Nov 13 '18 at 16:50












  • 1





    convert_variables_to_constants prunes the graph and removes everything not needed to compute the given outputs (using extract_sub_graph). Make sure that all the nodes you want are necessary for the given outputs, or otherwise you can directly add more nodes as outputs to make sure they get included.

    – jdehesa
    Nov 13 '18 at 11:30












  • @jdehesa thanks. How can I include a necessary node to the output graph?

    – mohamad danesh
    Nov 13 '18 at 16:48











  • When you call convert_variables_to_constants, add the nodes you want to include to output_node_names.

    – jdehesa
    Nov 13 '18 at 16:50







1




1





convert_variables_to_constants prunes the graph and removes everything not needed to compute the given outputs (using extract_sub_graph). Make sure that all the nodes you want are necessary for the given outputs, or otherwise you can directly add more nodes as outputs to make sure they get included.

– jdehesa
Nov 13 '18 at 11:30






convert_variables_to_constants prunes the graph and removes everything not needed to compute the given outputs (using extract_sub_graph). Make sure that all the nodes you want are necessary for the given outputs, or otherwise you can directly add more nodes as outputs to make sure they get included.

– jdehesa
Nov 13 '18 at 11:30














@jdehesa thanks. How can I include a necessary node to the output graph?

– mohamad danesh
Nov 13 '18 at 16:48





@jdehesa thanks. How can I include a necessary node to the output graph?

– mohamad danesh
Nov 13 '18 at 16:48













When you call convert_variables_to_constants, add the nodes you want to include to output_node_names.

– jdehesa
Nov 13 '18 at 16:50





When you call convert_variables_to_constants, add the nodes you want to include to output_node_names.

– jdehesa
Nov 13 '18 at 16:50












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%2f53276197%2fkeyerror-in-freeze-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















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%2f53276197%2fkeyerror-in-freeze-model%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

Use pre created SQLite database for Android project in kotlin

Darth Vader #20

Ondo