Axis parameter in the Keras backend sum












1












$begingroup$


In Keras custom loss function, I often see axis parameter is set to -1.



def custom_loss(y_true, y_pred):
intersection = K.sum(K.abs(y_true * y_pred), axis=-1)


I always thought that it should be 0, as 0 axis represents the batch. So why is set to -1?










share|improve this question







New contributor




KarateKid is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.







$endgroup$

















    1












    $begingroup$


    In Keras custom loss function, I often see axis parameter is set to -1.



    def custom_loss(y_true, y_pred):
    intersection = K.sum(K.abs(y_true * y_pred), axis=-1)


    I always thought that it should be 0, as 0 axis represents the batch. So why is set to -1?










    share|improve this question







    New contributor




    KarateKid is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
    Check out our Code of Conduct.







    $endgroup$















      1












      1








      1





      $begingroup$


      In Keras custom loss function, I often see axis parameter is set to -1.



      def custom_loss(y_true, y_pred):
      intersection = K.sum(K.abs(y_true * y_pred), axis=-1)


      I always thought that it should be 0, as 0 axis represents the batch. So why is set to -1?










      share|improve this question







      New contributor




      KarateKid is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.







      $endgroup$




      In Keras custom loss function, I often see axis parameter is set to -1.



      def custom_loss(y_true, y_pred):
      intersection = K.sum(K.abs(y_true * y_pred), axis=-1)


      I always thought that it should be 0, as 0 axis represents the batch. So why is set to -1?







      keras






      share|improve this question







      New contributor




      KarateKid is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.











      share|improve this question







      New contributor




      KarateKid is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      share|improve this question




      share|improve this question






      New contributor




      KarateKid is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.









      asked yesterday









      KarateKidKarateKid

      1183




      1183




      New contributor




      KarateKid is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.





      New contributor





      KarateKid is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






      KarateKid is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
      Check out our Code of Conduct.






















          1 Answer
          1






          active

          oldest

          votes


















          0












          $begingroup$

          Because y_true and y_pred have shapes (N,). Where N is the number of examples. By setting the axis to -1 you are calculating the sum over the last dimension, which happens to be over N (which is the batch)






          share|improve this answer








          New contributor




          Gonzalo Hernandez is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
          Check out our Code of Conduct.






          $endgroup$













            Your Answer





            StackExchange.ifUsing("editor", function () {
            return StackExchange.using("mathjaxEditing", function () {
            StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix) {
            StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
            });
            });
            }, "mathjax-editing");

            StackExchange.ready(function() {
            var channelOptions = {
            tags: "".split(" "),
            id: "557"
            };
            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: false,
            noModals: true,
            showLowRepImageUploadWarning: true,
            reputationToPostImages: null,
            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
            });


            }
            });






            KarateKid is a new contributor. Be nice, and check out our Code of Conduct.










            draft saved

            draft discarded


















            StackExchange.ready(
            function () {
            StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f45875%2faxis-parameter-in-the-keras-backend-sum%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












            $begingroup$

            Because y_true and y_pred have shapes (N,). Where N is the number of examples. By setting the axis to -1 you are calculating the sum over the last dimension, which happens to be over N (which is the batch)






            share|improve this answer








            New contributor




            Gonzalo Hernandez is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
            Check out our Code of Conduct.






            $endgroup$


















              0












              $begingroup$

              Because y_true and y_pred have shapes (N,). Where N is the number of examples. By setting the axis to -1 you are calculating the sum over the last dimension, which happens to be over N (which is the batch)






              share|improve this answer








              New contributor




              Gonzalo Hernandez is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
              Check out our Code of Conduct.






              $endgroup$
















                0












                0








                0





                $begingroup$

                Because y_true and y_pred have shapes (N,). Where N is the number of examples. By setting the axis to -1 you are calculating the sum over the last dimension, which happens to be over N (which is the batch)






                share|improve this answer








                New contributor




                Gonzalo Hernandez is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
                Check out our Code of Conduct.






                $endgroup$



                Because y_true and y_pred have shapes (N,). Where N is the number of examples. By setting the axis to -1 you are calculating the sum over the last dimension, which happens to be over N (which is the batch)







                share|improve this answer








                New contributor




                Gonzalo Hernandez is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
                Check out our Code of Conduct.









                share|improve this answer



                share|improve this answer






                New contributor




                Gonzalo Hernandez is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
                Check out our Code of Conduct.









                answered yesterday









                Gonzalo HernandezGonzalo Hernandez

                11




                11




                New contributor




                Gonzalo Hernandez is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
                Check out our Code of Conduct.





                New contributor





                Gonzalo Hernandez is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
                Check out our Code of Conduct.






                Gonzalo Hernandez is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
                Check out our Code of Conduct.






















                    KarateKid is a new contributor. Be nice, and check out our Code of Conduct.










                    draft saved

                    draft discarded


















                    KarateKid is a new contributor. Be nice, and check out our Code of Conduct.













                    KarateKid is a new contributor. Be nice, and check out our Code of Conduct.












                    KarateKid is a new contributor. Be nice, and check out our Code of Conduct.
















                    Thanks for contributing an answer to Data Science Stack Exchange!


                    • 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.


                    Use MathJax to format equations. MathJax reference.


                    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%2fdatascience.stackexchange.com%2fquestions%2f45875%2faxis-parameter-in-the-keras-backend-sum%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

                    How to label and detect the document text images

                    Vallis Paradisi

                    Tabula Rosettana