Deep Learning: Progress-saving, UE4 integration, and preparing for testing questions












0















After making a new network, I run it with the training data. The weights have updated permanently, right? WRONG! If I run it again, I get pretty much the exact same results, 0 improvement. How do I keep my progress after training? Let's say I've saved progress, my network has improved. How do I deploy it to a gam? How do I put Python code into C++ code for a UE4 game, and how do I integrate it into say a bot? My CNN/Q-Learning hybrid trains on visuals from other games to predict the best next move. If I were to somehow insert it into my code and run it, it has the training code with the training datasets. Do I have to redo the code for testing? Wouldn't that again lose all my progress? My current QLCNN is made for a person to monitor it, since it outputs loss and charts and other sorts of data. Is the main code similar to a header file in C++ or Java where I have to make another file that actually runs it?










share|improve this question





























    0















    After making a new network, I run it with the training data. The weights have updated permanently, right? WRONG! If I run it again, I get pretty much the exact same results, 0 improvement. How do I keep my progress after training? Let's say I've saved progress, my network has improved. How do I deploy it to a gam? How do I put Python code into C++ code for a UE4 game, and how do I integrate it into say a bot? My CNN/Q-Learning hybrid trains on visuals from other games to predict the best next move. If I were to somehow insert it into my code and run it, it has the training code with the training datasets. Do I have to redo the code for testing? Wouldn't that again lose all my progress? My current QLCNN is made for a person to monitor it, since it outputs loss and charts and other sorts of data. Is the main code similar to a header file in C++ or Java where I have to make another file that actually runs it?










    share|improve this question



























      0












      0








      0








      After making a new network, I run it with the training data. The weights have updated permanently, right? WRONG! If I run it again, I get pretty much the exact same results, 0 improvement. How do I keep my progress after training? Let's say I've saved progress, my network has improved. How do I deploy it to a gam? How do I put Python code into C++ code for a UE4 game, and how do I integrate it into say a bot? My CNN/Q-Learning hybrid trains on visuals from other games to predict the best next move. If I were to somehow insert it into my code and run it, it has the training code with the training datasets. Do I have to redo the code for testing? Wouldn't that again lose all my progress? My current QLCNN is made for a person to monitor it, since it outputs loss and charts and other sorts of data. Is the main code similar to a header file in C++ or Java where I have to make another file that actually runs it?










      share|improve this question
















      After making a new network, I run it with the training data. The weights have updated permanently, right? WRONG! If I run it again, I get pretty much the exact same results, 0 improvement. How do I keep my progress after training? Let's say I've saved progress, my network has improved. How do I deploy it to a gam? How do I put Python code into C++ code for a UE4 game, and how do I integrate it into say a bot? My CNN/Q-Learning hybrid trains on visuals from other games to predict the best next move. If I were to somehow insert it into my code and run it, it has the training code with the training datasets. Do I have to redo the code for testing? Wouldn't that again lose all my progress? My current QLCNN is made for a person to monitor it, since it outputs loss and charts and other sorts of data. Is the main code similar to a header file in C++ or Java where I have to make another file that actually runs it?







      optimization deep-learning integration






      share|improve this question















      share|improve this question













      share|improve this question




      share|improve this question








      edited Jan 3 at 1:30









      braaterAfrikaaner

      1,070517




      1,070517










      asked Jan 1 at 17:27









      Rasmit DevkotaRasmit Devkota

      14




      14
























          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%2f53997483%2fdeep-learning-progress-saving-ue4-integration-and-preparing-for-testing-quest%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%2f53997483%2fdeep-learning-progress-saving-ue4-integration-and-preparing-for-testing-quest%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

          Angular Downloading a file using contenturl with Basic Authentication

          Olmecas

          Can't read property showImagePicker of undefined in react native iOS