Why do I need to feed a value for placeholder if my output doesn't depend on it












0















Say I have following simple neural network. I have narrowed it down.



def Network(in1, in2, is_train):

dense1 = tf.layers.dense(in1, 100, activation=tf.nn.relu)
feed_tensor = tf.cond(is_train > 0, lambda: dense1, lambda: in2)
output = tf.layers.dense(feed_tensor, 3, activation=tf.nn.relu)
return output


First I train the neural network by feeding the values for all 3 tensors.



opt = tf.train.AdamOptimizer(learn_rate).minimize(loss)
sess.run(opt, feed_dict={in1: input1, in2: input2, is_train: 1})


Then I feed feed values only for in2 and is_train and try to observe the output.



out = (output, feed_dict={in2: input2, is_train: 0})


Ideally when is_train = 0 it should assign the value of in2 tensor to the feed_tensor, and there is no requirement to feed a value to in1.



However if I run the above, I get 'You must feed a value for placeholder tensor' error.



Can you explain why this happens and a possible way to get rid of this.



Specifically what I want is to select a tensor to be fed to the next layer depending on whether it's training time or not.



EDIT: Will this problem be resolved by feeding a dummy tensor to in1?










share|improve this question





























    0















    Say I have following simple neural network. I have narrowed it down.



    def Network(in1, in2, is_train):

    dense1 = tf.layers.dense(in1, 100, activation=tf.nn.relu)
    feed_tensor = tf.cond(is_train > 0, lambda: dense1, lambda: in2)
    output = tf.layers.dense(feed_tensor, 3, activation=tf.nn.relu)
    return output


    First I train the neural network by feeding the values for all 3 tensors.



    opt = tf.train.AdamOptimizer(learn_rate).minimize(loss)
    sess.run(opt, feed_dict={in1: input1, in2: input2, is_train: 1})


    Then I feed feed values only for in2 and is_train and try to observe the output.



    out = (output, feed_dict={in2: input2, is_train: 0})


    Ideally when is_train = 0 it should assign the value of in2 tensor to the feed_tensor, and there is no requirement to feed a value to in1.



    However if I run the above, I get 'You must feed a value for placeholder tensor' error.



    Can you explain why this happens and a possible way to get rid of this.



    Specifically what I want is to select a tensor to be fed to the next layer depending on whether it's training time or not.



    EDIT: Will this problem be resolved by feeding a dummy tensor to in1?










    share|improve this question



























      0












      0








      0








      Say I have following simple neural network. I have narrowed it down.



      def Network(in1, in2, is_train):

      dense1 = tf.layers.dense(in1, 100, activation=tf.nn.relu)
      feed_tensor = tf.cond(is_train > 0, lambda: dense1, lambda: in2)
      output = tf.layers.dense(feed_tensor, 3, activation=tf.nn.relu)
      return output


      First I train the neural network by feeding the values for all 3 tensors.



      opt = tf.train.AdamOptimizer(learn_rate).minimize(loss)
      sess.run(opt, feed_dict={in1: input1, in2: input2, is_train: 1})


      Then I feed feed values only for in2 and is_train and try to observe the output.



      out = (output, feed_dict={in2: input2, is_train: 0})


      Ideally when is_train = 0 it should assign the value of in2 tensor to the feed_tensor, and there is no requirement to feed a value to in1.



      However if I run the above, I get 'You must feed a value for placeholder tensor' error.



      Can you explain why this happens and a possible way to get rid of this.



      Specifically what I want is to select a tensor to be fed to the next layer depending on whether it's training time or not.



      EDIT: Will this problem be resolved by feeding a dummy tensor to in1?










      share|improve this question
















      Say I have following simple neural network. I have narrowed it down.



      def Network(in1, in2, is_train):

      dense1 = tf.layers.dense(in1, 100, activation=tf.nn.relu)
      feed_tensor = tf.cond(is_train > 0, lambda: dense1, lambda: in2)
      output = tf.layers.dense(feed_tensor, 3, activation=tf.nn.relu)
      return output


      First I train the neural network by feeding the values for all 3 tensors.



      opt = tf.train.AdamOptimizer(learn_rate).minimize(loss)
      sess.run(opt, feed_dict={in1: input1, in2: input2, is_train: 1})


      Then I feed feed values only for in2 and is_train and try to observe the output.



      out = (output, feed_dict={in2: input2, is_train: 0})


      Ideally when is_train = 0 it should assign the value of in2 tensor to the feed_tensor, and there is no requirement to feed a value to in1.



      However if I run the above, I get 'You must feed a value for placeholder tensor' error.



      Can you explain why this happens and a possible way to get rid of this.



      Specifically what I want is to select a tensor to be fed to the next layer depending on whether it's training time or not.



      EDIT: Will this problem be resolved by feeding a dummy tensor to in1?







      python tensorflow






      share|improve this question















      share|improve this question













      share|improve this question




      share|improve this question








      edited Nov 14 '18 at 11:19







      avin

















      asked Nov 13 '18 at 18:19









      avinavin

      284




      284
























          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%2f53287259%2fwhy-do-i-need-to-feed-a-value-for-placeholder-if-my-output-doesnt-depend-on-it%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%2f53287259%2fwhy-do-i-need-to-feed-a-value-for-placeholder-if-my-output-doesnt-depend-on-it%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

          Xamarin.iOS Cant Deploy on Iphone

          Glorious Revolution

          Dulmage-Mendelsohn matrix decomposition in Python