Why I need pre-trained weight in transfer learning? The Next CEO of Stack Overflow2019 Community Moderator ElectionWhere to find pre-trained models for transfer learningWhy is input preprocessing in VGG16 in Keras not 1/255.0Why do pre-trained CNNs use low image resolution?Transfer learning: Poor performance with last layer replacedMissing outputs in multiple-output neural netHow to properly mean-center my dataIntermediate layer output from pretrained TensorFlow modelPre-trained CNN for one-shot learningDoes it make sense to train a convolutional neural network on lo-res, use on hi-res pictures?How to use pre-trained weights to initialize the custom CNN?

How to avoid supervisors with prejudiced views?

"Eavesdropping" vs "Listen in on"

Why don't programming languages automatically manage the synchronous/asynchronous problem?

Which one is the true statement?

Is it professional to write unrelated content in an almost-empty email?

Calculate the Mean mean of two numbers

How to get the last not-null value in an ordered column of a huge table?

How to set page number in right side in chapter title page?

How did some of my text get highlighted with a magenta background?

Why the last AS PATH item always is `I` or `?`?

Can I board the first leg of the flight without having final country's visa?

Why is information "lost" when it got into a black hole?

Sulfuric acid symmetry point group

What connection does MS Office have to Netscape Navigator?

Can Sneak Attack be used when hitting with an improvised weapon?

Do scriptures give a method to recognize a truly self-realized person/jivanmukta?

Towers in the ocean; How deep can they be built?

Does destroying a Lich's phylactery destroy the soul within it?

Is it ever safe to open a suspicious HTML file (e.g. email attachment)?

How many extra stops do monopods offer for tele photographs?

Is there an equivalent of cd - for cp or mv

Help! I cannot understand this game’s notations!

Computationally populating tables with probability data

Can I calculate next year's exemptions based on this year's refund/amount owed?



Why I need pre-trained weight in transfer learning?



The Next CEO of Stack Overflow
2019 Community Moderator ElectionWhere to find pre-trained models for transfer learningWhy is input preprocessing in VGG16 in Keras not 1/255.0Why do pre-trained CNNs use low image resolution?Transfer learning: Poor performance with last layer replacedMissing outputs in multiple-output neural netHow to properly mean-center my dataIntermediate layer output from pretrained TensorFlow modelPre-trained CNN for one-shot learningDoes it make sense to train a convolutional neural network on lo-res, use on hi-res pictures?How to use pre-trained weights to initialize the custom CNN?










0












$begingroup$


I need a little help. I use a Mask-RCNN. I choosed backbone:resnet50. And downloaded Download COCO pre-trained weight.



Why I need pre-trained weight in transfer learning.
Transfer learning aproach is to train a base network and then copy its first layers of a target.



So: my base network is resnet50 and I copy first layers to Mask RCNN. So why I need pre-trained weight for example coco pre-trained weights.



I understand it so: I copy layers and pre-trained weights from resnet.



Thanks in advance.






deep-learning cnn transfer-learning






share











$endgroup$
















    0












    $begingroup$


    I need a little help. I use a Mask-RCNN. I choosed backbone:resnet50. And downloaded Download COCO pre-trained weight.



    Why I need pre-trained weight in transfer learning.
    Transfer learning aproach is to train a base network and then copy its first layers of a target.



    So: my base network is resnet50 and I copy first layers to Mask RCNN. So why I need pre-trained weight for example coco pre-trained weights.



    I understand it so: I copy layers and pre-trained weights from resnet.



    Thanks in advance.






    deep-learning cnn transfer-learning






    share











    $endgroup$














      0












      0








      0





      $begingroup$


      I need a little help. I use a Mask-RCNN. I choosed backbone:resnet50. And downloaded Download COCO pre-trained weight.



      Why I need pre-trained weight in transfer learning.
      Transfer learning aproach is to train a base network and then copy its first layers of a target.



      So: my base network is resnet50 and I copy first layers to Mask RCNN. So why I need pre-trained weight for example coco pre-trained weights.



      I understand it so: I copy layers and pre-trained weights from resnet.



      Thanks in advance.






      deep-learning cnn transfer-learning






      share











      $endgroup$




      I need a little help. I use a Mask-RCNN. I choosed backbone:resnet50. And downloaded Download COCO pre-trained weight.



      Why I need pre-trained weight in transfer learning.
      Transfer learning aproach is to train a base network and then copy its first layers of a target.



      So: my base network is resnet50 and I copy first layers to Mask RCNN. So why I need pre-trained weight for example coco pre-trained weights.



      I understand it so: I copy layers and pre-trained weights from resnet.



      Thanks in advance.






      deep-learning cnn transfer-learning




      deep-learning cnn transfer-learning





      share














      share












      share



      share








      edited 27 mins ago







      Badum

















      asked 1 hour ago









      BadumBadum

      114




      114




















          0






          active

          oldest

          votes












          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
          );



          );













          draft saved

          draft discarded


















          StackExchange.ready(
          function ()
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f48317%2fwhy-i-need-pre-trained-weight-in-transfer-learning%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 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%2f48317%2fwhy-i-need-pre-trained-weight-in-transfer-learning%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







          -