Using tf.batch_scatter_add in Keras












2















I'm looking for a way to use tf.scatter_add with Keras batches.
Shape of outputs: (?, 1000) and shapes of indices and updates are (?, 100) each.



Try1: Using Keras tensors



vals = tf.scatter_add(outputs, indices, updates)


This throws an error:




'Tensor' object has no attribute '_lazy_read'




Try2: Tried using k.variable which should be updatable



vals = K.variable(outputs)
vals = tf.scatter_add(vals, inputs[1], inputs[2])



ValueError: initial_value must have a shape specified:

Tensor("scatter_add_43/zeros_like:0", shape=(?, 1000), dtype=float32))




Any clues? Scatter_add and batch_scatter_add result in the same errors. Will I need to write a custom layer for this? Seems like even that will run into one of the above errors.










share|improve this question





























    2















    I'm looking for a way to use tf.scatter_add with Keras batches.
    Shape of outputs: (?, 1000) and shapes of indices and updates are (?, 100) each.



    Try1: Using Keras tensors



    vals = tf.scatter_add(outputs, indices, updates)


    This throws an error:




    'Tensor' object has no attribute '_lazy_read'




    Try2: Tried using k.variable which should be updatable



    vals = K.variable(outputs)
    vals = tf.scatter_add(vals, inputs[1], inputs[2])



    ValueError: initial_value must have a shape specified:

    Tensor("scatter_add_43/zeros_like:0", shape=(?, 1000), dtype=float32))




    Any clues? Scatter_add and batch_scatter_add result in the same errors. Will I need to write a custom layer for this? Seems like even that will run into one of the above errors.










    share|improve this question



























      2












      2








      2








      I'm looking for a way to use tf.scatter_add with Keras batches.
      Shape of outputs: (?, 1000) and shapes of indices and updates are (?, 100) each.



      Try1: Using Keras tensors



      vals = tf.scatter_add(outputs, indices, updates)


      This throws an error:




      'Tensor' object has no attribute '_lazy_read'




      Try2: Tried using k.variable which should be updatable



      vals = K.variable(outputs)
      vals = tf.scatter_add(vals, inputs[1], inputs[2])



      ValueError: initial_value must have a shape specified:

      Tensor("scatter_add_43/zeros_like:0", shape=(?, 1000), dtype=float32))




      Any clues? Scatter_add and batch_scatter_add result in the same errors. Will I need to write a custom layer for this? Seems like even that will run into one of the above errors.










      share|improve this question
















      I'm looking for a way to use tf.scatter_add with Keras batches.
      Shape of outputs: (?, 1000) and shapes of indices and updates are (?, 100) each.



      Try1: Using Keras tensors



      vals = tf.scatter_add(outputs, indices, updates)


      This throws an error:




      'Tensor' object has no attribute '_lazy_read'




      Try2: Tried using k.variable which should be updatable



      vals = K.variable(outputs)
      vals = tf.scatter_add(vals, inputs[1], inputs[2])



      ValueError: initial_value must have a shape specified:

      Tensor("scatter_add_43/zeros_like:0", shape=(?, 1000), dtype=float32))




      Any clues? Scatter_add and batch_scatter_add result in the same errors. Will I need to write a custom layer for this? Seems like even that will run into one of the above errors.







      python tensorflow keras






      share|improve this question















      share|improve this question













      share|improve this question




      share|improve this question








      edited Nov 26 '18 at 7:23









      barbsan

      2,45131223




      2,45131223










      asked Nov 25 '18 at 18:00









      N. SawantN. Sawant

      111




      111
























          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%2f53470309%2fusing-tf-batch-scatter-add-in-keras%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%2f53470309%2fusing-tf-batch-scatter-add-in-keras%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

          404 Error Contact Form 7 ajax form submitting

          How to know if a Active Directory user can login interactively

          TypeError: fit_transform() missing 1 required positional argument: 'X'