Keras Error when Concatenating layers in functional mode

Multi tool use
Multi tool use












1















I'm attempting to concatenate two layers. According to the documentation, the following should be correct.



import tensorflow.keras as K

input = K.Input(shape=(self.state_dimensions(),))
shared_features = K.layers.Dense(10,activation='tanh')
x = K.layers.Dense(10, activation='tanh')(input)
a = shared_features(x[0:10])
b = shared_features(x[10:20])
output = K.layers.Concatenate()([a,b])
actor_model = K.Model(inputs=input, outputs=output)


However, in the last line, this error appears:



ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer` (thus holding past layer metadata). Found: Tensor("concatenate/concat:0", shape=(?, 6), dtype=float32)









share|improve this question



























    1















    I'm attempting to concatenate two layers. According to the documentation, the following should be correct.



    import tensorflow.keras as K

    input = K.Input(shape=(self.state_dimensions(),))
    shared_features = K.layers.Dense(10,activation='tanh')
    x = K.layers.Dense(10, activation='tanh')(input)
    a = shared_features(x[0:10])
    b = shared_features(x[10:20])
    output = K.layers.Concatenate()([a,b])
    actor_model = K.Model(inputs=input, outputs=output)


    However, in the last line, this error appears:



    ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer` (thus holding past layer metadata). Found: Tensor("concatenate/concat:0", shape=(?, 6), dtype=float32)









    share|improve this question

























      1












      1








      1








      I'm attempting to concatenate two layers. According to the documentation, the following should be correct.



      import tensorflow.keras as K

      input = K.Input(shape=(self.state_dimensions(),))
      shared_features = K.layers.Dense(10,activation='tanh')
      x = K.layers.Dense(10, activation='tanh')(input)
      a = shared_features(x[0:10])
      b = shared_features(x[10:20])
      output = K.layers.Concatenate()([a,b])
      actor_model = K.Model(inputs=input, outputs=output)


      However, in the last line, this error appears:



      ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer` (thus holding past layer metadata). Found: Tensor("concatenate/concat:0", shape=(?, 6), dtype=float32)









      share|improve this question














      I'm attempting to concatenate two layers. According to the documentation, the following should be correct.



      import tensorflow.keras as K

      input = K.Input(shape=(self.state_dimensions(),))
      shared_features = K.layers.Dense(10,activation='tanh')
      x = K.layers.Dense(10, activation='tanh')(input)
      a = shared_features(x[0:10])
      b = shared_features(x[10:20])
      output = K.layers.Concatenate()([a,b])
      actor_model = K.Model(inputs=input, outputs=output)


      However, in the last line, this error appears:



      ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer` (thus holding past layer metadata). Found: Tensor("concatenate/concat:0", shape=(?, 6), dtype=float32)






      tensorflow keras






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Jan 2 at 15:58









      gufftangufftan

      88312




      88312
























          1 Answer
          1






          active

          oldest

          votes


















          0














          Tensors a and b contain operations outside layers. All operations must be inside keras layers.



          a = K.layers.Lambda(lambda x: x[:10])(x)
          b = K.layers.Lambda(lambda x: x[10:20])(x)

          a = shared_features(a)
          b = shared_features(b)


          You will have problems as you're splitting the tensor in the batch size dimension. K.layers.Concatenate() doesn't work on the batch dimension. You will end up with a different number of samples at the end.



          You probably want x[:,0:10] and x[:,10:20]






          share|improve this answer























            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%2f54009380%2fkeras-error-when-concatenating-layers-in-functional-mode%23new-answer', 'question_page');
            }
            );

            Post as a guest















            Required, but never shown

























            1 Answer
            1






            active

            oldest

            votes








            1 Answer
            1






            active

            oldest

            votes









            active

            oldest

            votes






            active

            oldest

            votes









            0














            Tensors a and b contain operations outside layers. All operations must be inside keras layers.



            a = K.layers.Lambda(lambda x: x[:10])(x)
            b = K.layers.Lambda(lambda x: x[10:20])(x)

            a = shared_features(a)
            b = shared_features(b)


            You will have problems as you're splitting the tensor in the batch size dimension. K.layers.Concatenate() doesn't work on the batch dimension. You will end up with a different number of samples at the end.



            You probably want x[:,0:10] and x[:,10:20]






            share|improve this answer




























              0














              Tensors a and b contain operations outside layers. All operations must be inside keras layers.



              a = K.layers.Lambda(lambda x: x[:10])(x)
              b = K.layers.Lambda(lambda x: x[10:20])(x)

              a = shared_features(a)
              b = shared_features(b)


              You will have problems as you're splitting the tensor in the batch size dimension. K.layers.Concatenate() doesn't work on the batch dimension. You will end up with a different number of samples at the end.



              You probably want x[:,0:10] and x[:,10:20]






              share|improve this answer


























                0












                0








                0







                Tensors a and b contain operations outside layers. All operations must be inside keras layers.



                a = K.layers.Lambda(lambda x: x[:10])(x)
                b = K.layers.Lambda(lambda x: x[10:20])(x)

                a = shared_features(a)
                b = shared_features(b)


                You will have problems as you're splitting the tensor in the batch size dimension. K.layers.Concatenate() doesn't work on the batch dimension. You will end up with a different number of samples at the end.



                You probably want x[:,0:10] and x[:,10:20]






                share|improve this answer













                Tensors a and b contain operations outside layers. All operations must be inside keras layers.



                a = K.layers.Lambda(lambda x: x[:10])(x)
                b = K.layers.Lambda(lambda x: x[10:20])(x)

                a = shared_features(a)
                b = shared_features(b)


                You will have problems as you're splitting the tensor in the batch size dimension. K.layers.Concatenate() doesn't work on the batch dimension. You will end up with a different number of samples at the end.



                You probably want x[:,0:10] and x[:,10:20]







                share|improve this answer












                share|improve this answer



                share|improve this answer










                answered Jan 2 at 16:10









                Daniel MöllerDaniel Möller

                37.2k671108




                37.2k671108
































                    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%2f54009380%2fkeras-error-when-concatenating-layers-in-functional-mode%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







                    jqA2 YhpRGk7 Lu,BgxL JR3daM nB9,HudIcQZQ,kWCn59llJmbwqQ kRn6n X8,Lukz
                    3QfheeNe sUj,7gQVDnV0Vggat229kZ bel8 gV9KcvvH

                    Popular posts from this blog

                    Monofisismo

                    Angular Downloading a file using contenturl with Basic Authentication

                    Olmecas