Why can't I use data augmentation with a pretrained convnet?












1












$begingroup$


Reading Deep Learning with Python by François Chollet. In section 5.3.1, we've instantiated a pretrained convnet, VGG16, and are given two options to proceed:




A) Running the convolutional base over your dataset, recording its
output to a Numpy array on disk, and then using this data as input to
a standalone, densely connected classifier similar to those you saw in
part 1 of this book. This solution is fast and cheap to run, because
it only requires running the convolutional base once for every input
image, and the convolutional base is by far the most expensive part of
the pipeline. But for the same reason, this technique won’t allow you
to use data augmentation.



B) Extending the model you have (conv_base) by adding Dense layers on
top, and running the whole thing end to end on the input data. This
will allow you to use data augmentation, because every input image
goes through the convolutional base every time it’s seen by the model.
But for the same reason, this technique is far more expensive than the
first.




Why can't I use data augmentation to generate more training data from existing training samples then go with option A? Seems like I can run the VGG16 base over my augmented dataset and use the output as the input to a standalone densely connected classifier.










share|improve this question







New contributor




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







$endgroup$

















    1












    $begingroup$


    Reading Deep Learning with Python by François Chollet. In section 5.3.1, we've instantiated a pretrained convnet, VGG16, and are given two options to proceed:




    A) Running the convolutional base over your dataset, recording its
    output to a Numpy array on disk, and then using this data as input to
    a standalone, densely connected classifier similar to those you saw in
    part 1 of this book. This solution is fast and cheap to run, because
    it only requires running the convolutional base once for every input
    image, and the convolutional base is by far the most expensive part of
    the pipeline. But for the same reason, this technique won’t allow you
    to use data augmentation.



    B) Extending the model you have (conv_base) by adding Dense layers on
    top, and running the whole thing end to end on the input data. This
    will allow you to use data augmentation, because every input image
    goes through the convolutional base every time it’s seen by the model.
    But for the same reason, this technique is far more expensive than the
    first.




    Why can't I use data augmentation to generate more training data from existing training samples then go with option A? Seems like I can run the VGG16 base over my augmented dataset and use the output as the input to a standalone densely connected classifier.










    share|improve this question







    New contributor




    Ivan Lee 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





      $begingroup$


      Reading Deep Learning with Python by François Chollet. In section 5.3.1, we've instantiated a pretrained convnet, VGG16, and are given two options to proceed:




      A) Running the convolutional base over your dataset, recording its
      output to a Numpy array on disk, and then using this data as input to
      a standalone, densely connected classifier similar to those you saw in
      part 1 of this book. This solution is fast and cheap to run, because
      it only requires running the convolutional base once for every input
      image, and the convolutional base is by far the most expensive part of
      the pipeline. But for the same reason, this technique won’t allow you
      to use data augmentation.



      B) Extending the model you have (conv_base) by adding Dense layers on
      top, and running the whole thing end to end on the input data. This
      will allow you to use data augmentation, because every input image
      goes through the convolutional base every time it’s seen by the model.
      But for the same reason, this technique is far more expensive than the
      first.




      Why can't I use data augmentation to generate more training data from existing training samples then go with option A? Seems like I can run the VGG16 base over my augmented dataset and use the output as the input to a standalone densely connected classifier.










      share|improve this question







      New contributor




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







      $endgroup$




      Reading Deep Learning with Python by François Chollet. In section 5.3.1, we've instantiated a pretrained convnet, VGG16, and are given two options to proceed:




      A) Running the convolutional base over your dataset, recording its
      output to a Numpy array on disk, and then using this data as input to
      a standalone, densely connected classifier similar to those you saw in
      part 1 of this book. This solution is fast and cheap to run, because
      it only requires running the convolutional base once for every input
      image, and the convolutional base is by far the most expensive part of
      the pipeline. But for the same reason, this technique won’t allow you
      to use data augmentation.



      B) Extending the model you have (conv_base) by adding Dense layers on
      top, and running the whole thing end to end on the input data. This
      will allow you to use data augmentation, because every input image
      goes through the convolutional base every time it’s seen by the model.
      But for the same reason, this technique is far more expensive than the
      first.




      Why can't I use data augmentation to generate more training data from existing training samples then go with option A? Seems like I can run the VGG16 base over my augmented dataset and use the output as the input to a standalone densely connected classifier.







      convnet beginner data-augmentation






      share|improve this question







      New contributor




      Ivan Lee 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




      Ivan Lee 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




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









      asked yesterday









      Ivan LeeIvan Lee

      393




      393




      New contributor




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





      New contributor





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






      Ivan Lee 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


















          3












          $begingroup$

          Found the answer in stats.stackexchange.com. Hopefully this helps anyone else with the same question.



          feature extraction: freezing convolutional base vs. training on extracted features






          share|improve this answer










          New contributor




          Ivan Lee 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
            });


            }
            });






            Ivan Lee 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%2f49069%2fwhy-cant-i-use-data-augmentation-with-a-pretrained-convnet%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









            3












            $begingroup$

            Found the answer in stats.stackexchange.com. Hopefully this helps anyone else with the same question.



            feature extraction: freezing convolutional base vs. training on extracted features






            share|improve this answer










            New contributor




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






            $endgroup$


















              3












              $begingroup$

              Found the answer in stats.stackexchange.com. Hopefully this helps anyone else with the same question.



              feature extraction: freezing convolutional base vs. training on extracted features






              share|improve this answer










              New contributor




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






              $endgroup$
















                3












                3








                3





                $begingroup$

                Found the answer in stats.stackexchange.com. Hopefully this helps anyone else with the same question.



                feature extraction: freezing convolutional base vs. training on extracted features






                share|improve this answer










                New contributor




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






                $endgroup$



                Found the answer in stats.stackexchange.com. Hopefully this helps anyone else with the same question.



                feature extraction: freezing convolutional base vs. training on extracted features







                share|improve this answer










                New contributor




                Ivan Lee 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








                edited yesterday









                Esmailian

                3,031320




                3,031320






                New contributor




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









                answered yesterday









                Ivan LeeIvan Lee

                393




                393




                New contributor




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





                New contributor





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






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






















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










                    draft saved

                    draft discarded


















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













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












                    Ivan Lee 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%2f49069%2fwhy-cant-i-use-data-augmentation-with-a-pretrained-convnet%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