loss weights for classifcation and regression heads in CNN











up vote
0
down vote

favorite












I have a CNN with a classification head with 2 outputs which uses categorical cross entropy and a regression head with 2 outputs which uses mean-squared error for the losses.



The loss for the CNN is a linear combination of the losses for the classification head and the regression head:



cnn_loss = W_class * loss_classification + W_regression * loss_regression



Is there a good way to determine or commonly used values for W_class and W_regression?










share|improve this question


























    up vote
    0
    down vote

    favorite












    I have a CNN with a classification head with 2 outputs which uses categorical cross entropy and a regression head with 2 outputs which uses mean-squared error for the losses.



    The loss for the CNN is a linear combination of the losses for the classification head and the regression head:



    cnn_loss = W_class * loss_classification + W_regression * loss_regression



    Is there a good way to determine or commonly used values for W_class and W_regression?










    share|improve this question
























      up vote
      0
      down vote

      favorite









      up vote
      0
      down vote

      favorite











      I have a CNN with a classification head with 2 outputs which uses categorical cross entropy and a regression head with 2 outputs which uses mean-squared error for the losses.



      The loss for the CNN is a linear combination of the losses for the classification head and the regression head:



      cnn_loss = W_class * loss_classification + W_regression * loss_regression



      Is there a good way to determine or commonly used values for W_class and W_regression?










      share|improve this question













      I have a CNN with a classification head with 2 outputs which uses categorical cross entropy and a regression head with 2 outputs which uses mean-squared error for the losses.



      The loss for the CNN is a linear combination of the losses for the classification head and the regression head:



      cnn_loss = W_class * loss_classification + W_regression * loss_regression



      Is there a good way to determine or commonly used values for W_class and W_regression?







      classification regression conv-neural-network loss






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Nov 8 at 3:07









      user3731622

      1,34611431




      1,34611431





























          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',
          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%2f53200986%2floss-weights-for-classifcation-and-regression-heads-in-cnn%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown






























          active

          oldest

          votes













          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.





          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%2f53200986%2floss-weights-for-classifcation-and-regression-heads-in-cnn%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







          這個網誌中的熱門文章

          Tangent Lines Diagram Along Smooth Curve

          Yusuf al-Mu'taman ibn Hud

          Zucchini