How can I get best val_acc and val_loss simultaneously in CNN using keras?












1














I've used ModelCheckpoint(file_path, monitor='val_acc', verbose=1, save_best_only=True, mode='max') to get the max val_acc. So, when i run my program I get a many of sample such as:




  1. val_acc = 0.92857 & val_loss = 0.2495,

  2. val_acc = 0.98750 & val_loss = 0.6820.


So, it takes 2 no., although it's val_loss in large.
How can I choose the no. 1 with lower val_loss?
Alternatively, how can i choose the best fitted model keeping val_acc and val_loss value in mind?










share|improve this question



























    1














    I've used ModelCheckpoint(file_path, monitor='val_acc', verbose=1, save_best_only=True, mode='max') to get the max val_acc. So, when i run my program I get a many of sample such as:




    1. val_acc = 0.92857 & val_loss = 0.2495,

    2. val_acc = 0.98750 & val_loss = 0.6820.


    So, it takes 2 no., although it's val_loss in large.
    How can I choose the no. 1 with lower val_loss?
    Alternatively, how can i choose the best fitted model keeping val_acc and val_loss value in mind?










    share|improve this question

























      1












      1








      1







      I've used ModelCheckpoint(file_path, monitor='val_acc', verbose=1, save_best_only=True, mode='max') to get the max val_acc. So, when i run my program I get a many of sample such as:




      1. val_acc = 0.92857 & val_loss = 0.2495,

      2. val_acc = 0.98750 & val_loss = 0.6820.


      So, it takes 2 no., although it's val_loss in large.
      How can I choose the no. 1 with lower val_loss?
      Alternatively, how can i choose the best fitted model keeping val_acc and val_loss value in mind?










      share|improve this question













      I've used ModelCheckpoint(file_path, monitor='val_acc', verbose=1, save_best_only=True, mode='max') to get the max val_acc. So, when i run my program I get a many of sample such as:




      1. val_acc = 0.92857 & val_loss = 0.2495,

      2. val_acc = 0.98750 & val_loss = 0.6820.


      So, it takes 2 no., although it's val_loss in large.
      How can I choose the no. 1 with lower val_loss?
      Alternatively, how can i choose the best fitted model keeping val_acc and val_loss value in mind?







      keras






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Nov 12 at 14:23









      Tariqul Islam

      85




      85
























          1 Answer
          1






          active

          oldest

          votes


















          0














          You should really just factor one of them for your checkpoint. However, you could just create two callbacks and save the network based on both metrics.



          call_acc = ModelCheckpoint(weights.{epoch:02d}-{val_acc:.2f}.hdf5, monitor='val_acc', save_best_only=True, mode='max')
          call_loss = ModelCheckpoint(weights.{epoch:02d}-{val_loss:.2f}.hdf5, monitor='val_loss', save_best_only=True, mode='min')
          model.fit(X, Y, epochs, batch_siz, callbacks=[call_loss, call_acc])





          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%2f53264181%2fhow-can-i-get-best-val-acc-and-val-loss-simultaneously-in-cnn-using-keras%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














            You should really just factor one of them for your checkpoint. However, you could just create two callbacks and save the network based on both metrics.



            call_acc = ModelCheckpoint(weights.{epoch:02d}-{val_acc:.2f}.hdf5, monitor='val_acc', save_best_only=True, mode='max')
            call_loss = ModelCheckpoint(weights.{epoch:02d}-{val_loss:.2f}.hdf5, monitor='val_loss', save_best_only=True, mode='min')
            model.fit(X, Y, epochs, batch_siz, callbacks=[call_loss, call_acc])





            share|improve this answer


























              0














              You should really just factor one of them for your checkpoint. However, you could just create two callbacks and save the network based on both metrics.



              call_acc = ModelCheckpoint(weights.{epoch:02d}-{val_acc:.2f}.hdf5, monitor='val_acc', save_best_only=True, mode='max')
              call_loss = ModelCheckpoint(weights.{epoch:02d}-{val_loss:.2f}.hdf5, monitor='val_loss', save_best_only=True, mode='min')
              model.fit(X, Y, epochs, batch_siz, callbacks=[call_loss, call_acc])





              share|improve this answer
























                0












                0








                0






                You should really just factor one of them for your checkpoint. However, you could just create two callbacks and save the network based on both metrics.



                call_acc = ModelCheckpoint(weights.{epoch:02d}-{val_acc:.2f}.hdf5, monitor='val_acc', save_best_only=True, mode='max')
                call_loss = ModelCheckpoint(weights.{epoch:02d}-{val_loss:.2f}.hdf5, monitor='val_loss', save_best_only=True, mode='min')
                model.fit(X, Y, epochs, batch_siz, callbacks=[call_loss, call_acc])





                share|improve this answer












                You should really just factor one of them for your checkpoint. However, you could just create two callbacks and save the network based on both metrics.



                call_acc = ModelCheckpoint(weights.{epoch:02d}-{val_acc:.2f}.hdf5, monitor='val_acc', save_best_only=True, mode='max')
                call_loss = ModelCheckpoint(weights.{epoch:02d}-{val_loss:.2f}.hdf5, monitor='val_loss', save_best_only=True, mode='min')
                model.fit(X, Y, epochs, batch_siz, callbacks=[call_loss, call_acc])






                share|improve this answer












                share|improve this answer



                share|improve this answer










                answered Nov 12 at 20:14









                Kurtis Streutker

                48028




                48028






























                    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.





                    Some of your past answers have not been well-received, and you're in danger of being blocked from answering.


                    Please pay close attention to the following guidance:


                    • 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%2f53264181%2fhow-can-i-get-best-val-acc-and-val-loss-simultaneously-in-cnn-using-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

                    Bressuire

                    Vorschmack

                    Quarantine